{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling/papers/ran/8","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":8,"pages_in_order":19,"rows_per_page":100,"rows":[701,800],"of":1894,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modeling/papers/ran/1","prev":"/task/language-modeling/papers/ran/7","next":"/task/language-modeling/papers/ran/9","papers":[{"url":"/paper/dwell-in-the-beginning-how-language-models","slug":"dwell-in-the-beginning-how-language-models","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","date":"2024-04-05","arxiv_id":"2404.04163","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dwell-in-the-beginning-how-language-models#ran","syntology_url":"https://syntology.ai/paper/2404.04163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04163"}},"official":{"repos":["cxcscmu/longembeddinganalysis"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/physics-event-classification-using-large","slug":"physics-event-classification-using-large","title":"Physics Event Classification Using Large Language Models","date":"2024-04-05","arxiv_id":"2404.05752","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/physics-event-classification-using-large#ran","syntology_url":"https://syntology.ai/paper/2404.05752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05752"}},"official":{"repos":["ai4eic/ai4eichackathon2023-streamlit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}},"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sailor-open-language-models-for-south-east","slug":"sailor-open-language-models-for-south-east","title":"Sailor: Open Language Models for South-East Asia","date":"2024-04-04","arxiv_id":"2404.03608","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/sailor-open-language-models-for-south-east#ran","syntology_url":"https://syntology.ai/paper/2404.03608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03608"}},"official":{"repos":["epfllm/megatron-llm","sail-sg/sailor-llm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/autowebglm-bootstrap-and-reinforce-a-large","slug":"autowebglm-bootstrap-and-reinforce-a-large","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","date":"2024-04-04","arxiv_id":"2404.03648","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/autowebglm-bootstrap-and-reinforce-a-large#ran","syntology_url":"https://syntology.ai/paper/2404.03648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03648"}},"official":{"repos":["thudm/autowebglm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-evolution-an-iterated-learning","slug":"language-model-evolution-an-iterated-learning","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","date":"2024-04-04","arxiv_id":"2404.04286","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-model-evolution-an-iterated-learning#ran","syntology_url":"https://syntology.ai/paper/2404.04286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04286"}},"official":{"repos":["joshua-ren/iicl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lvlm-intrepret-an-interpretability-tool-for","slug":"lvlm-intrepret-an-interpretability-tool-for","title":"LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models","date":"2024-04-03","arxiv_id":"2404.03118","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lvlm-intrepret-an-interpretability-tool-for#ran","syntology_url":"https://syntology.ai/paper/2404.03118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03118"}},"official":{"repos":["IntelLabs/lvlm-interpret"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-organized-agents-a-llm-multi-agent","slug":"self-organized-agents-a-llm-multi-agent","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","date":"2024-04-02","arxiv_id":"2404.02183","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-organized-agents-a-llm-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2404.02183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02183"}},"official":{"repos":["tsukushiai/self-organized-agent"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/do-language-models-plan-ahead-for-future","slug":"do-language-models-plan-ahead-for-future","title":"Do language models plan ahead for future tokens?","date":"2024-04-01","arxiv_id":"2404.00859","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/do-language-models-plan-ahead-for-future#ran","syntology_url":"https://syntology.ai/paper/2404.00859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00859"}},"official":{"repos":["wiwu2390/futuregpt2-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/lipsum-ft-robust-fine-tuning-of-zero-shot","slug":"lipsum-ft-robust-fine-tuning-of-zero-shot","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","date":"2024-04-01","arxiv_id":"2404.00860","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lipsum-ft-robust-fine-tuning-of-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2404.00860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00860"}},"official":{"repos":["cs-giung/lipsum-ft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-by-correction-efficient-tuning-task","slug":"learning-by-correction-efficient-tuning-task","title":"Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning","date":"2024-04-01","arxiv_id":"2404.00909","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-by-correction-efficient-tuning-task#ran","syntology_url":"https://syntology.ai/paper/2404.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00909"}},"official":{"repos":["shtuplus/iccc_cvpr2024"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/regularized-best-of-n-sampling-to-mitigate","slug":"regularized-best-of-n-sampling-to-mitigate","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","date":"2024-04-01","arxiv_id":"2404.01054","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/regularized-best-of-n-sampling-to-mitigate#ran","syntology_url":"https://syntology.ai/paper/2404.01054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01054"}},"official":{"repos":["CyberAgentAILab/regularized-bon"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/direct-preference-optimization-of-video-large","slug":"direct-preference-optimization-of-video-large","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","date":"2024-04-01","arxiv_id":"2404.01258","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direct-preference-optimization-of-video-large#ran","syntology_url":"https://syntology.ai/paper/2404.01258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01258"}},"official":{"repos":["riflezhang/llava-hound-dpo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/developing-safe-and-responsible-large","slug":"developing-safe-and-responsible-large","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","date":"2024-04-01","arxiv_id":"2404.01399","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/developing-safe-and-responsible-large#ran","syntology_url":"https://syntology.ai/paper/2404.01399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01399"}},"official":{"repos":["shainarazavi/safe-responsible-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-plan-for-language-modeling-from","slug":"learning-to-plan-for-language-modeling-from","title":"Learning to Plan for Language Modeling from Unlabeled Data","date":"2024-03-31","arxiv_id":"2404.00614","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-to-plan-for-language-modeling-from#ran","syntology_url":"https://syntology.ai/paper/2404.00614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00614"}},"official":{"repos":["natithan/learning-to-plan-for-language-modeling-from-unlabeled-data"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/wavllm-towards-robust-and-adaptive-speech","slug":"wavllm-towards-robust-and-adaptive-speech","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","date":"2024-03-31","arxiv_id":"2404.00656","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wavllm-towards-robust-and-adaptive-speech#ran","syntology_url":"https://syntology.ai/paper/2404.00656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00656"}},"official":{"repos":["microsoft/speecht5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dilm-distilling-dataset-into-language-model","slug":"dilm-distilling-dataset-into-language-model","title":"DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation","date":"2024-03-30","arxiv_id":"2404.00264","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dilm-distilling-dataset-into-language-model#ran","syntology_url":"https://syntology.ai/paper/2404.00264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00264"}},"official":{"repos":["arumaekawa/dilm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/do-vision-language-models-understand-compound","slug":"do-vision-language-models-understand-compound","title":"Do Vision-Language Models Understand Compound Nouns?","date":"2024-03-30","arxiv_id":"2404.00419","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-vision-language-models-understand-compound#ran","syntology_url":"https://syntology.ai/paper/2404.00419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00419"}},"official":{"repos":["sonalkum/compun"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/metaie-distilling-a-meta-model-from-llm-for","slug":"metaie-distilling-a-meta-model-from-llm-for","title":"MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks","date":"2024-03-30","arxiv_id":"2404.00457","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metaie-distilling-a-meta-model-from-llm-for#ran","syntology_url":"https://syntology.ai/paper/2404.00457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00457"}},"official":{"repos":["komeijiforce/metaie"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mango-a-benchmark-for-evaluating-mapping-and","slug":"mango-a-benchmark-for-evaluating-mapping-and","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","date":"2024-03-29","arxiv_id":"2403.19913","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mango-a-benchmark-for-evaluating-mapping-and#ran","syntology_url":"https://syntology.ai/paper/2403.19913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19913"}},"official":{"repos":["oaklight/mango"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/h2rsvlm-towards-helpful-and-honest-remote","slug":"h2rsvlm-towards-helpful-and-honest-remote","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","date":"2024-03-29","arxiv_id":"2403.20213","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h2rsvlm-towards-helpful-and-honest-remote#ran","syntology_url":"https://syntology.ai/paper/2403.20213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20213"}},"official":{"repos":["opendatalab/h2rsvlm","opendatalab/vhm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-gemma-accelerating-multimodal","slug":"llava-gemma-accelerating-multimodal","title":"LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model","date":"2024-03-29","arxiv_id":"2404.01331","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llava-gemma-accelerating-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.01331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01331"}},"official":{"repos":["intellabs/multimodal_cognitive_ai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/star-gate-teaching-language-models-to-ask","slug":"star-gate-teaching-language-models-to-ask","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","date":"2024-03-28","arxiv_id":"2403.19154","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/star-gate-teaching-language-models-to-ask#ran","syntology_url":"https://syntology.ai/paper/2403.19154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19154"}},"official":{"repos":["scandukuri/assistant-gate"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tablellm-enabling-tabular-data-manipulation","slug":"tablellm-enabling-tabular-data-manipulation","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","date":"2024-03-28","arxiv_id":"2403.19318","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tablellm-enabling-tabular-data-manipulation#ran","syntology_url":"https://syntology.ai/paper/2403.19318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19318"}},"official":{"repos":["TableLLM/TableLLM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-enhanced-knowledge-editing-for","slug":"retrieval-enhanced-knowledge-editing-for","title":"Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering","date":"2024-03-28","arxiv_id":"2403.19631","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/retrieval-enhanced-knowledge-editing-for#ran","syntology_url":"https://syntology.ai/paper/2403.19631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19631"}},"official":{"repos":["sycny/rae"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-feature-circuits-discovering-and","slug":"sparse-feature-circuits-discovering-and","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","date":"2024-03-28","arxiv_id":"2403.19647","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sparse-feature-circuits-discovering-and#ran","syntology_url":"https://syntology.ai/paper/2403.19647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19647"}},"official":{"repos":["saprmarks/feature-circuits"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/localizing-paragraph-memorization-in-language","slug":"localizing-paragraph-memorization-in-language","title":"Localizing Paragraph Memorization in Language Models","date":"2024-03-28","arxiv_id":"2403.19851","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/localizing-paragraph-memorization-in-language#ran","syntology_url":"https://syntology.ai/paper/2403.19851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19851"}},"official":{"repos":["googleinterns/localizing-paragraph-memorization"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mechanisms-of-non-factual-hallucinations-in","slug":"mechanisms-of-non-factual-hallucinations-in","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","date":"2024-03-27","arxiv_id":"2403.18167","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mechanisms-of-non-factual-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2403.18167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18167"}},"official":{"repos":["jadeleiyu/lm_hallucination_mechanisms"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sequential-recommendation-with-latent","slug":"sequential-recommendation-with-latent","title":"Sequential Recommendation with Latent Relations based on Large Language Model","date":"2024-03-27","arxiv_id":"2403.18348","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sequential-recommendation-with-latent#ran","syntology_url":"https://syntology.ai/paper/2403.18348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18348"}},"official":{"repos":["ysh-1998/lrd"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","slug":"an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","arxiv_id":"2403.18406","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-image-grid-can-be-worth-a-video-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}},"official":{"repos":["imagegridworth/IG-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/biomedlm-a-2-7b-parameter-language-model","slug":"biomedlm-a-2-7b-parameter-language-model","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","date":"2024-03-27","arxiv_id":"2403.18421","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/biomedlm-a-2-7b-parameter-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.18421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18421"}},"official":{"repos":["stanford-crfm/biomedlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-language-beat-numerical-regression","slug":"can-language-beat-numerical-regression","title":"Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction","date":"2024-03-27","arxiv_id":"2403.18447","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-language-beat-numerical-regression#ran","syntology_url":"https://syntology.ai/paper/2403.18447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18447"}},"official":{"repos":["inhwanbae/lmtrajectory"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/if-clip-could-talk-understanding-vision","slug":"if-clip-could-talk-understanding-vision","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","date":"2024-03-25","arxiv_id":"2403.16442","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/if-clip-could-talk-understanding-vision#ran","syntology_url":"https://syntology.ai/paper/2403.16442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16442"}},"official":{"repos":["batsresearch/ex2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-with-human-judgement-the-role-of","slug":"aligning-with-human-judgement-the-role-of","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","date":"2024-03-25","arxiv_id":"2403.16950","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-with-human-judgement-the-role-of#ran","syntology_url":"https://syntology.ai/paper/2403.16950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16950"}},"official":{"repos":["cambridgeltl/pairs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-mixing-laws-optimizing-data-mixtures-by","slug":"data-mixing-laws-optimizing-data-mixtures-by","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","date":"2024-03-25","arxiv_id":"2403.16952","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/data-mixing-laws-optimizing-data-mixtures-by#ran","syntology_url":"https://syntology.ai/paper/2403.16952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16952"}},"official":{"repos":["yegcjs/mixinglaws"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/voicecraft-zero-shot-speech-editing-and-text","slug":"voicecraft-zero-shot-speech-editing-and-text","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","date":"2024-03-25","arxiv_id":"2403.16973","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/voicecraft-zero-shot-speech-editing-and-text#ran","syntology_url":"https://syntology.ai/paper/2403.16973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16973"}},"official":{"repos":["jasonppy/voicecraft"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/monotonic-paraphrasing-improves","slug":"monotonic-paraphrasing-improves","title":"Monotonic Paraphrasing Improves Generalization of Language Model Prompting","date":"2024-03-24","arxiv_id":"2403.16038","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/monotonic-paraphrasing-improves#ran","syntology_url":"https://syntology.ai/paper/2403.16038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16038"}},"official":{"repos":["luka-group/monopara"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wikifactdiff-a-large-realistic-and-temporally","slug":"wikifactdiff-a-large-realistic-and-temporally","title":"WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models","date":"2024-03-21","arxiv_id":"2403.14364","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/wikifactdiff-a-large-realistic-and-temporally#ran","syntology_url":"https://syntology.ai/paper/2403.14364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14364"}},"official":{"repos":["orange-opensource/wikifactdiff"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/regularized-adaptive-momentum-dual-averaging","slug":"regularized-adaptive-momentum-dual-averaging","title":"Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network","date":"2024-03-21","arxiv_id":"2403.14398","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":1,"n_ran_checked":4,"n_instrument":8,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":16,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/regularized-adaptive-momentum-dual-averaging#ran","syntology_url":"https://syntology.ai/paper/2403.14398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14398"}},"official":{"repos":["ismoptgroup/ramda","ismoptgroup/ramda_exp"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/cobra-extending-mamba-to-multi-modal-large","slug":"cobra-extending-mamba-to-multi-modal-large","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","date":"2024-03-21","arxiv_id":"2403.14520","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cobra-extending-mamba-to-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2403.14520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14520"}},"official":{"repos":["h-zhao1997/cobra"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llamafactory-unified-efficient-fine-tuning-of","slug":"llamafactory-unified-efficient-fine-tuning-of","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","date":"2024-03-20","arxiv_id":"2403.13372","repositories_listed":8,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/llamafactory-unified-efficient-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2403.13372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13372"}},"official":{"repos":["hiyouga/llama-factory"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-large-language-model-enhanced-sequential","slug":"a-large-language-model-enhanced-sequential","title":"A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation","date":"2024-03-20","arxiv_id":"2403.13574","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-large-language-model-enhanced-sequential#ran","syntology_url":"https://syntology.ai/paper/2403.13574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13574"}},"official":{"repos":["rucaibox/lsvcr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-3-large-language-model-based-task-and","slug":"llm-3-large-language-model-based-task-and","title":"LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning","date":"2024-03-18","arxiv_id":"2403.11552","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-3-large-language-model-based-task-and#ran","syntology_url":"https://syntology.ai/paper/2403.11552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11552"}},"official":{"repos":["assassinws/llm-tamp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/subjective-aligned-dateset-and-metric-for","slug":"subjective-aligned-dateset-and-metric-for","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","date":"2024-03-18","arxiv_id":"2403.11956","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/subjective-aligned-dateset-and-metric-for#ran","syntology_url":"https://syntology.ai/paper/2403.11956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11956"}},"official":{"repos":["qmme/t2vqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selfie-self-interpretation-of-large-language","slug":"selfie-self-interpretation-of-large-language","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","date":"2024-03-16","arxiv_id":"2403.10949","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selfie-self-interpretation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2403.10949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10949"}},"official":{"repos":["tonychenxyz/selfie"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficientvmamba-atrous-selective-scan-for","slug":"efficientvmamba-atrous-selective-scan-for","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","date":"2024-03-15","arxiv_id":"2403.09977","repositories_listed":1,"syntology":{"n":18,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":18,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/efficientvmamba-atrous-selective-scan-for#ran","syntology_url":"https://syntology.ai/paper/2403.09977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09977"}},"official":{"repos":["terrypei/efficientvmamba"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-medical-multi-modal-contrastive","slug":"improving-medical-multi-modal-contrastive","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","date":"2024-03-15","arxiv_id":"2403.10153","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/improving-medical-multi-modal-contrastive#ran","syntology_url":"https://syntology.ai/paper/2403.10153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10153"}},"official":{"repos":["ykumards/eclip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-region-language-pretraining-for","slug":"generative-region-language-pretraining-for","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","date":"2024-03-15","arxiv_id":"2403.10191","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generative-region-language-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2403.10191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10191"}},"official":{"repos":["foundationvision/generateu"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/avibench-towards-evaluating-the-robustness-of","slug":"avibench-towards-evaluating-the-robustness-of","title":"B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions","date":"2024-03-14","arxiv_id":"2403.09346","repositories_listed":1,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":14,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/avibench-towards-evaluating-the-robustness-of#ran","syntology_url":"https://syntology.ai/paper/2403.09346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09346"}},"official":{"repos":["zhanghao5201/b-avibench"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transformers-get-stable-an-end-to-end-signal","slug":"transformers-get-stable-an-end-to-end-signal","title":"Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models","date":"2024-03-14","arxiv_id":"2403.09635","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/transformers-get-stable-an-end-to-end-signal#ran","syntology_url":"https://syntology.ai/paper/2403.09635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09635"}},"official":{"repos":["akhilkedia/tranformersgetstable"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-was-your-prompt-a-remote-keylogging","slug":"what-was-your-prompt-a-remote-keylogging","title":"What Was Your Prompt? A Remote Keylogging Attack on AI Assistants","date":"2024-03-14","arxiv_id":"2403.09751","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-was-your-prompt-a-remote-keylogging#ran","syntology_url":"https://syntology.ai/paper/2403.09751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09751"}},"official":{"repos":["royweiss1/GPT_Keylogger"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generative-pretrained-structured-transformers#ran","syntology_url":"https://syntology.ai/paper/2403.08293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08293"}},"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/coin-a-benchmark-of-continual-instruction","slug":"coin-a-benchmark-of-continual-instruction","title":"CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model","date":"2024-03-13","arxiv_id":"2403.08350","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coin-a-benchmark-of-continual-instruction#ran","syntology_url":"https://syntology.ai/paper/2403.08350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08350"}},"official":{"repos":["zackschen/coin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/smart-submodular-data-mixture-strategy-for","slug":"smart-submodular-data-mixture-strategy-for","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","date":"2024-03-13","arxiv_id":"2403.08370","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smart-submodular-data-mixture-strategy-for#ran","syntology_url":"https://syntology.ai/paper/2403.08370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08370"}},"official":{"repos":["kowndinya-renduchintala/smart"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/sotopia-p-interactive-learning-of-socially","slug":"sotopia-p-interactive-learning-of-socially","title":"SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents","date":"2024-03-13","arxiv_id":"2403.08715","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sotopia-p-interactive-learning-of-socially#ran","syntology_url":"https://syntology.ai/paper/2403.08715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08715"}},"official":{"repos":["sotopia-lab/sotopia-pi"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kebench-a-benchmark-on-knowledge-editing-for","slug":"kebench-a-benchmark-on-knowledge-editing-for","title":"VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark","date":"2024-03-12","arxiv_id":"2403.07350","repositories_listed":1,"syntology":{"n":25,"n_ran":22,"n_constructed":0,"n_ran_checked":16,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":5,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/kebench-a-benchmark-on-knowledge-editing-for#ran","syntology_url":"https://syntology.ai/paper/2403.07350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07350"}},"official":{"repos":["vlkeb/vlkeb"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/svd-llm-truncation-aware-singular-value","slug":"svd-llm-truncation-aware-singular-value","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","date":"2024-03-12","arxiv_id":"2403.07378","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/svd-llm-truncation-aware-singular-value#ran","syntology_url":"https://syntology.ai/paper/2403.07378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07378"}},"official":{"repos":["aiot-mlsys-lab/svd-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/chronos-learning-the-language-of-time-series","slug":"chronos-learning-the-language-of-time-series","title":"Chronos: Learning the Language of Time Series","date":"2024-03-12","arxiv_id":"2403.07815","repositories_listed":6,"syntology":{"n":28,"n_ran":23,"n_constructed":0,"n_ran_checked":22,"n_instrument":1,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":18,"n_pointer_only":5,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 1 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/chronos-learning-the-language-of-time-series#ran","syntology_url":"https://syntology.ai/paper/2403.07815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07815"}},"official":{"repos":["SalesforceAIResearch/uni2ts","amazon-science/chronos-forecasting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/beyond-text-frozen-large-language-models-in","slug":"beyond-text-frozen-large-language-models-in","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","date":"2024-03-12","arxiv_id":"2403.07874","repositories_listed":1,"syntology":{"n":26,"n_ran":17,"n_constructed":0,"n_ran_checked":6,"n_instrument":11,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":26,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/beyond-text-frozen-large-language-models-in#ran","syntology_url":"https://syntology.ai/paper/2403.07874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07874"}},"official":{"repos":["zh460045050/v2l-tokenizer"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/drivedreamer-2-llm-enhanced-world-models-for","slug":"drivedreamer-2-llm-enhanced-world-models-for","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","date":"2024-03-11","arxiv_id":"2403.06845","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/drivedreamer-2-llm-enhanced-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2403.06845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06845"}},"official":null}},{"url":"/paper/personalized-lora-for-human-centered-text","slug":"personalized-lora-for-human-centered-text","title":"Personalized LoRA for Human-Centered Text Understanding","date":"2024-03-10","arxiv_id":"2403.06208","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/personalized-lora-for-human-centered-text#ran","syntology_url":"https://syntology.ai/paper/2403.06208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06208"}},"official":{"repos":["yoyo-yun/plora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/clinicalmamba-a-generative-clinical-language","slug":"clinicalmamba-a-generative-clinical-language","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","date":"2024-03-09","arxiv_id":"2403.05795","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clinicalmamba-a-generative-clinical-language#ran","syntology_url":"https://syntology.ai/paper/2403.05795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05795"}},"official":{"repos":["whaleloops/clinicalmamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tapilot-crossing-benchmarking-and-evolving","slug":"tapilot-crossing-benchmarking-and-evolving","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","date":"2024-03-08","arxiv_id":"2403.05307","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tapilot-crossing-benchmarking-and-evolving#ran","syntology_url":"https://syntology.ai/paper/2403.05307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05307"}},"official":{"repos":["tapilot-crossing/tapilot_code"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bias-augmented-consistency-training-reduces#ran","syntology_url":"https://syntology.ai/paper/2403.05518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05518"}},"official":{"repos":["raybears/cot-transparency"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/embodied-understanding-of-driving-scenarios","slug":"embodied-understanding-of-driving-scenarios","title":"Embodied Understanding of Driving Scenarios","date":"2024-03-07","arxiv_id":"2403.04593","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/embodied-understanding-of-driving-scenarios#ran","syntology_url":"https://syntology.ai/paper/2403.04593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04593"}},"official":{"repos":["opendrivelab/elm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cat-enhancing-multimodal-large-language-model","slug":"cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cat-enhancing-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"official":{"repos":["rikeilong/bay-cat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/yi-open-foundation-models-by-01-ai","slug":"yi-open-foundation-models-by-01-ai","title":"Yi: Open Foundation Models by 01.AI","date":"2024-03-07","arxiv_id":"2403.04652","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/yi-open-foundation-models-by-01-ai#ran","syntology_url":"https://syntology.ai/paper/2403.04652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04652"}},"official":{"repos":["01-ai/yi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/unitable-towards-a-unified-framework-for","slug":"unitable-towards-a-unified-framework-for","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","date":"2024-03-07","arxiv_id":"2403.04822","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unitable-towards-a-unified-framework-for#ran","syntology_url":"https://syntology.ai/paper/2403.04822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04822"}},"official":{"repos":["poloclub/unitable"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/injecagent-benchmarking-indirect-prompt","slug":"injecagent-benchmarking-indirect-prompt","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","date":"2024-03-05","arxiv_id":"2403.02691","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/injecagent-benchmarking-indirect-prompt#ran","syntology_url":"https://syntology.ai/paper/2403.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02691"}},"official":{"repos":["uiuc-kang-lab/injecagent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/android-in-the-zoo-chain-of-action-thought","slug":"android-in-the-zoo-chain-of-action-thought","title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","date":"2024-03-05","arxiv_id":"2403.02713","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/android-in-the-zoo-chain-of-action-thought#ran","syntology_url":"https://syntology.ai/paper/2403.02713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02713"}},"official":{"repos":["imnearth/coat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-of-llm-as-a-judge-for-llm","slug":"an-empirical-study-of-llm-as-a-judge-for-llm","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","date":"2024-03-05","arxiv_id":"2403.02839","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-empirical-study-of-llm-as-a-judge-for-llm#ran","syntology_url":"https://syntology.ai/paper/2403.02839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02839"}},"official":{"repos":["huihuichyan/unlimitedjudge"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-instruction-tuned-llms-with-fine","slug":"multi-modal-instruction-tuned-llms-with-fine","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","date":"2024-03-05","arxiv_id":"2403.02969","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-modal-instruction-tuned-llms-with-fine#ran","syntology_url":"https://syntology.ai/paper/2403.02969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02969"}},"official":{"repos":["jwh97nn/anyref"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-maximize-mutual-information-for-1","slug":"learning-to-maximize-mutual-information-for-1","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","date":"2024-03-05","arxiv_id":"2403.03348","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-maximize-mutual-information-for-1#ran","syntology_url":"https://syntology.ai/paper/2403.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03348"}},"official":{"repos":["xinchen9/cot_distillation_acl2024"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/found-in-the-middle-how-language-models-use","slug":"found-in-the-middle-how-language-models-use","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","date":"2024-03-05","arxiv_id":"2403.04797","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/found-in-the-middle-how-language-models-use#ran","syntology_url":"https://syntology.ai/paper/2403.04797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04797"}},"official":{"repos":["vita-group/ms-poe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-scale-protein-language-model-for","slug":"multi-scale-protein-language-model-for","title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","date":"2024-03-05","arxiv_id":"2403.12995","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-scale-protein-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2403.12995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12995"}},"official":{"repos":["zhengkangjie/esm-aa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/guardt2i-defending-text-to-image-models-from","slug":"guardt2i-defending-text-to-image-models-from","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","date":"2024-03-03","arxiv_id":"2403.01446","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/guardt2i-defending-text-to-image-models-from#ran","syntology_url":"https://syntology.ai/paper/2403.01446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01446"}},"official":{"repos":["cure-lab/guardt2i"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lab-large-scale-alignment-for-chatbots","slug":"lab-large-scale-alignment-for-chatbots","title":"LAB: Large-Scale Alignment for ChatBots","date":"2024-03-02","arxiv_id":"2403.01081","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lab-large-scale-alignment-for-chatbots#ran","syntology_url":"https://syntology.ai/paper/2403.01081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01081"}},"official":null}},{"url":"/paper/opengraph-towards-open-graph-foundation","slug":"opengraph-towards-open-graph-foundation","title":"OpenGraph: Towards Open Graph Foundation Models","date":"2024-03-02","arxiv_id":"2403.01121","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/opengraph-towards-open-graph-foundation#ran","syntology_url":"https://syntology.ai/paper/2403.01121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01121"}},"official":{"repos":["hkuds/opengraph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/intactkv-improving-large-language-model","slug":"intactkv-improving-large-language-model","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","date":"2024-03-02","arxiv_id":"2403.01241","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/intactkv-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.01241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01241"}},"official":{"repos":["ruikangliu/IntactKV"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/merging-text-transformer-models-from","slug":"merging-text-transformer-models-from","title":"Merging Text Transformer Models from Different Initializations","date":"2024-03-01","arxiv_id":"2403.00986","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/merging-text-transformer-models-from#ran","syntology_url":"https://syntology.ai/paper/2403.00986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00986"}},"official":{"repos":["nverma1/merging-text-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flexllm-a-system-for-co-serving-large","slug":"flexllm-a-system-for-co-serving-large","title":"FlexLLM: A System for Co-Serving Large Language Model Inference and Parameter-Efficient Finetuning","date":"2024-02-29","arxiv_id":"2402.18789","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/flexllm-a-system-for-co-serving-large#ran","syntology_url":"https://syntology.ai/paper/2402.18789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18789"}},"official":{"repos":["flexflow/flexflow"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/archer-training-language-model-agents-via","slug":"archer-training-language-model-agents-via","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","date":"2024-02-29","arxiv_id":"2402.19446","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/archer-training-language-model-agents-via#ran","syntology_url":"https://syntology.ai/paper/2402.19446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19446"}},"official":{"repos":["yifeizhou02/archer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rinalmo-general-purpose-rna-language-models","slug":"rinalmo-general-purpose-rna-language-models","title":"RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks","date":"2024-02-29","arxiv_id":"2403.00043","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rinalmo-general-purpose-rna-language-models#ran","syntology_url":"https://syntology.ai/paper/2403.00043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00043"}},"official":{"repos":["lbcb-sci/rinalmo","ml4bio/rna-fm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/resonance-rope-improving-context-length","slug":"resonance-rope-improving-context-length","title":"Resonance RoPE: Improving Context Length Generalization of Large Language Models","date":"2024-02-29","arxiv_id":"2403.00071","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/resonance-rope-improving-context-length#ran","syntology_url":"https://syntology.ai/paper/2403.00071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00071"}},"official":{"repos":["sheryc/resonance_rope"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/characterizing-truthfulness-in-large-language","slug":"characterizing-truthfulness-in-large-language","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","date":"2024-02-28","arxiv_id":"2402.18048","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/characterizing-truthfulness-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.18048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18048"}},"official":{"repos":["fanyin3639/lid-hallucinationdetection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-information-refinement-training","slug":"unsupervised-information-refinement-training","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","date":"2024-02-28","arxiv_id":"2402.18150","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-information-refinement-training#ran","syntology_url":"https://syntology.ai/paper/2402.18150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18150"}},"official":{"repos":["xsc1234/info-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cogbench-a-large-language-model-walks-into-a","slug":"cogbench-a-large-language-model-walks-into-a","title":"CogBench: a large language model walks into a psychology lab","date":"2024-02-28","arxiv_id":"2402.18225","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cogbench-a-large-language-model-walks-into-a#ran","syntology_url":"https://syntology.ai/paper/2402.18225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18225"}},"official":{"repos":["juliancodaforno/cogbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-language-models-are-versatile","slug":"diffusion-language-models-are-versatile","title":"Diffusion Language Models Are Versatile Protein Learners","date":"2024-02-28","arxiv_id":"2402.18567","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-language-models-are-versatile#ran","syntology_url":"https://syntology.ai/paper/2402.18567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18567"}},"official":{"repos":["bytedance/dplm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounding-language-models-for-visual-entity","slug":"grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","arxiv_id":"2402.18695","repositories_listed":1,"syntology":{"n":26,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/grounding-language-models-for-visual-entity#ran","syntology_url":"https://syntology.ai/paper/2402.18695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18695"}},"official":{"repos":["mrzilinxiao/autover"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-is-accurate-generation","slug":"retrieval-is-accurate-generation","title":"Retrieval is Accurate Generation","date":"2024-02-27","arxiv_id":"2402.17532","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-is-accurate-generation#ran","syntology_url":"https://syntology.ai/paper/2402.17532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17532"}},"official":{"repos":["gmftbygmftby/copyisallyouneed"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","unlocated"]}}},{"url":"/paper/songcomposer-a-large-language-model-for-lyric","slug":"songcomposer-a-large-language-model-for-lyric","title":"SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition","date":"2024-02-27","arxiv_id":"2402.17645","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/songcomposer-a-large-language-model-for-lyric#ran","syntology_url":"https://syntology.ai/paper/2402.17645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17645"}},"official":{"repos":["pjlab-songcomposer/songcomposer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ravel-evaluating-interpretability-methods-on","slug":"ravel-evaluating-interpretability-methods-on","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","date":"2024-02-27","arxiv_id":"2402.17700","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ravel-evaluating-interpretability-methods-on#ran","syntology_url":"https://syntology.ai/paper/2402.17700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17700"}},"official":{"repos":["explanare/ravel"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tower-an-open-multilingual-large-language","slug":"tower-an-open-multilingual-large-language","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","date":"2024-02-27","arxiv_id":"2402.17733","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tower-an-open-multilingual-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.17733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17733"}},"official":{"repos":["deep-spin/tower-eval","epfllm/megatron-llm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shapellm-universal-3d-object-understanding","slug":"shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/enhancing-efficiency-in-sparse-models-with","slug":"enhancing-efficiency-in-sparse-models-with","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","date":"2024-02-27","arxiv_id":"2403.18926","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-efficiency-in-sparse-models-with#ran","syntology_url":"https://syntology.ai/paper/2403.18926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18926"}},"official":{"repos":["ysngki/xmoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/long-context-language-modeling-with-parallel","slug":"long-context-language-modeling-with-parallel","title":"Long-Context Language Modeling with Parallel Context Encoding","date":"2024-02-26","arxiv_id":"2402.16617","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/long-context-language-modeling-with-parallel#ran","syntology_url":"https://syntology.ai/paper/2402.16617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16617"}},"official":{"repos":["princeton-nlp/cepe"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/repoagent-an-llm-powered-open-source","slug":"repoagent-an-llm-powered-open-source","title":"RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation","date":"2024-02-26","arxiv_id":"2402.16667","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/repoagent-an-llm-powered-open-source#ran","syntology_url":"https://syntology.ai/paper/2402.16667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16667"}},"official":{"repos":["openbmb/repoagent"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}}],"record_sha256":"c37930851a90bb88fae55ba08ad9154a2aaa3f2f81ea808897ceaeef57de9f07","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}