{"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-modelling/papers/ran/6","list_of":"/task/language-modelling","task":"Language Modelling","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":6,"pages_in_order":25,"rows_per_page":100,"rows":[501,600],"of":2428,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling/papers/ran/1","prev":"/task/language-modelling/papers/ran/5","next":"/task/language-modelling/papers/ran/7","papers":[{"url":"/paper/explore-the-potential-of-clip-for-training","slug":"explore-the-potential-of-clip-for-training","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","date":"2024-07-11","arxiv_id":"2407.08268","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/explore-the-potential-of-clip-for-training#ran","syntology_url":"https://syntology.ai/paper/2407.08268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08268"}},"official":{"repos":["leaves162/cliptrase"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/autobencher-creating-salient-novel-difficult","slug":"autobencher-creating-salient-novel-difficult","title":"AutoBencher: Creating Salient, Novel, Difficult Datasets for Language Models","date":"2024-07-11","arxiv_id":"2407.08351","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autobencher-creating-salient-novel-difficult#ran","syntology_url":"https://syntology.ai/paper/2407.08351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08351"}},"official":{"repos":["XiangLi1999/AutoBencher"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seed-story-multimodal-long-story-generation","slug":"seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08683","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":17,"phrase":"14 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seed-story-multimodal-long-story-generation#ran","syntology_url":"https://syntology.ai/paper/2407.08683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08683"}},"official":{"repos":["tencentarc/seed-story"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ida-vlm-towards-movie-understanding-via-id","slug":"ida-vlm-towards-movie-understanding-via-id","title":"IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model","date":"2024-07-10","arxiv_id":"2407.07577","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/ida-vlm-towards-movie-understanding-via-id#ran","syntology_url":"https://syntology.ai/paper/2407.07577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07577"}},"official":{"repos":["jiyt17/ida-vlm"],"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/paligemma-a-versatile-3b-vlm-for-transfer","slug":"paligemma-a-versatile-3b-vlm-for-transfer","title":"PaliGemma: A versatile 3B VLM for transfer","date":"2024-07-10","arxiv_id":"2407.07726","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/paligemma-a-versatile-3b-vlm-for-transfer#ran","syntology_url":"https://syntology.ai/paper/2407.07726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07726"}},"official":{"repos":["google-research/big_vision"],"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/training-on-the-test-task-confounds","slug":"training-on-the-test-task-confounds","title":"Training on the Test Task Confounds Evaluation and Emergence","date":"2024-07-10","arxiv_id":"2407.07890","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"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) · 3 unverified","sample_list":"/paper/training-on-the-test-task-confounds#ran","syntology_url":"https://syntology.ai/paper/2407.07890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07890"}},"official":{"repos":["socialfoundations/training-on-the-test-task"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cola-conditional-dropout-and-language-driven","slug":"cola-conditional-dropout-and-language-driven","title":"CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection","date":"2024-07-09","arxiv_id":"2407.06780","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cola-conditional-dropout-and-language-driven#ran","syntology_url":"https://syntology.ai/paper/2407.06780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06780"}},"official":{"repos":["ssecv/CoLA"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-self-instruct-synthetic-abstract","slug":"multimodal-self-instruct-synthetic-abstract","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","date":"2024-07-09","arxiv_id":"2407.07053","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/multimodal-self-instruct-synthetic-abstract#ran","syntology_url":"https://syntology.ai/paper/2407.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07053"}},"official":{"repos":["zwq2018/multi-modal-self-instruct"],"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/copybench-measuring-literal-and-non-literal","slug":"copybench-measuring-literal-and-non-literal","title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","date":"2024-07-09","arxiv_id":"2407.07087","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/copybench-measuring-literal-and-non-literal#ran","syntology_url":"https://syntology.ai/paper/2407.07087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07087"}},"official":{"repos":["chentong0/copy-bench"],"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/fbi-llm-scaling-up-fully-binarized-llms-from","slug":"fbi-llm-scaling-up-fully-binarized-llms-from","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","date":"2024-07-09","arxiv_id":"2407.07093","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"11 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fbi-llm-scaling-up-fully-binarized-llms-from#ran","syntology_url":"https://syntology.ai/paper/2407.07093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07093"}},"official":{"repos":["liqunma/fbi-llm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-retrieval-based-language-models-with","slug":"scaling-retrieval-based-language-models-with","title":"Scaling Retrieval-Based Language Models with a Trillion-Token Datastore","date":"2024-07-09","arxiv_id":"2407.12854","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-retrieval-based-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2407.12854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12854"}},"official":{"repos":["rulinshao/retrieval-scaling"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-speeding-up-language-model-evaluation","slug":"on-speeding-up-language-model-evaluation","title":"On Speeding Up Language Model Evaluation","date":"2024-07-08","arxiv_id":"2407.06172","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-speeding-up-language-model-evaluation#ran","syntology_url":"https://syntology.ai/paper/2407.06172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06172"}},"official":null}},{"url":"/paper/debunc-mitigating-hallucinations-in-large","slug":"debunc-mitigating-hallucinations-in-large","title":"DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics","date":"2024-07-08","arxiv_id":"2407.06426","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debunc-mitigating-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2407.06426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06426"}},"official":{"repos":["lukeyoffe/debunc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-single-transformer-for-scalable-vision","slug":"a-single-transformer-for-scalable-vision","title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","date":"2024-07-08","arxiv_id":"2407.06438","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":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/a-single-transformer-for-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2407.06438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06438"}},"official":{"repos":["yangyi-chen/solo"],"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/language-models-encode-collaborative-signals","slug":"language-models-encode-collaborative-signals","title":"Language Representations Can be What Recommenders Need: Findings and Potentials","date":"2024-07-07","arxiv_id":"2407.05441","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/language-models-encode-collaborative-signals#ran","syntology_url":"https://syntology.ai/paper/2407.05441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05441"}},"official":{"repos":["lehengthu/alpharec"],"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/enhancing-hallucination-detection-through","slug":"enhancing-hallucination-detection-through","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","date":"2024-07-07","arxiv_id":"2407.05474","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/enhancing-hallucination-detection-through#ran","syntology_url":"https://syntology.ai/paper/2407.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05474"}},"official":{"repos":["asappresearch/halugen"],"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/just-read-twice-closing-the-recall-gap-for","slug":"just-read-twice-closing-the-recall-gap-for","title":"Just read twice: closing the recall gap for recurrent language models","date":"2024-07-07","arxiv_id":"2407.05483","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/just-read-twice-closing-the-recall-gap-for#ran","syntology_url":"https://syntology.ai/paper/2407.05483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05483"}},"official":{"repos":["HazyResearch/prefix-linear-attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-perplexity-multi-dimensional-safety","slug":"beyond-perplexity-multi-dimensional-safety","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","date":"2024-07-06","arxiv_id":"2407.04965","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/beyond-perplexity-multi-dimensional-safety#ran","syntology_url":"https://syntology.ai/paper/2407.04965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04965"}},"official":{"repos":["zhichaoxu-shufe/beyond-perplexity-compression-safety-eval"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/shine-saliency-aware-hierarchical-negative","slug":"shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","arxiv_id":"2407.05118","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":13,"phrase":"11 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/shine-saliency-aware-hierarchical-negative#ran","syntology_url":"https://syntology.ai/paper/2407.05118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05118"}},"official":{"repos":["zxccade/shine"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-good-medical-coders","slug":"large-language-models-are-good-medical-coders","title":"Large language models are good medical coders, if provided with tools","date":"2024-07-06","arxiv_id":"2407.12849","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/large-language-models-are-good-medical-coders#ran","syntology_url":"https://syntology.ai/paper/2407.12849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12849"}},"official":{"repos":["ainativehealth/goodmedicalcoder"],"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/crafting-large-language-models-for-enhanced","slug":"crafting-large-language-models-for-enhanced","title":"Crafting Large Language Models for Enhanced Interpretability","date":"2024-07-05","arxiv_id":"2407.04307","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/crafting-large-language-models-for-enhanced#ran","syntology_url":"https://syntology.ai/paper/2407.04307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04307"}},"official":null}},{"url":"/paper/me-myself-and-ai-the-situational-awareness","slug":"me-myself-and-ai-the-situational-awareness","title":"Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs","date":"2024-07-05","arxiv_id":"2407.04694","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":7,"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/me-myself-and-ai-the-situational-awareness#ran","syntology_url":"https://syntology.ai/paper/2407.04694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04694"}},"official":{"repos":["lrudl/sad"],"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/spikellm-scaling-up-spiking-neural-network-to","slug":"spikellm-scaling-up-spiking-neural-network-to","title":"SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking","date":"2024-07-05","arxiv_id":"2407.04752","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":2,"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/spikellm-scaling-up-spiking-neural-network-to#ran","syntology_url":"https://syntology.ai/paper/2407.04752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04752"}},"official":null}},{"url":"/paper/minigpt-med-large-language-model-as-a-general","slug":"minigpt-med-large-language-model-as-a-general","title":"MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis","date":"2024-07-04","arxiv_id":"2407.04106","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt-med-large-language-model-as-a-general#ran","syntology_url":"https://syntology.ai/paper/2407.04106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04106"}},"official":{"repos":["vision-cair/minigpt-med"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-a-million-experts","slug":"mixture-of-a-million-experts","title":"Mixture of A Million Experts","date":"2024-07-04","arxiv_id":"2407.04153","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mixture-of-a-million-experts#ran","syntology_url":"https://syntology.ai/paper/2407.04153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04153"}},"official":null}},{"url":"/paper/on-the-client-preference-of-llm-fine-tuning","slug":"on-the-client-preference-of-llm-fine-tuning","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","date":"2024-07-03","arxiv_id":"2407.03038","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/on-the-client-preference-of-llm-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2407.03038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03038"}},"official":null}},{"url":"/paper/let-the-code-llm-edit-itself-when-you-edit","slug":"let-the-code-llm-edit-itself-when-you-edit","title":"Let the Code LLM Edit Itself When You Edit the Code","date":"2024-07-03","arxiv_id":"2407.03157","repositories_listed":0,"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/let-the-code-llm-edit-itself-when-you-edit#ran","syntology_url":"https://syntology.ai/paper/2407.03157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03157"}},"official":null}},{"url":"/paper/internlm-xcomposer-2-5-a-versatile-large","slug":"internlm-xcomposer-2-5-a-versatile-large","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","date":"2024-07-03","arxiv_id":"2407.03320","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":2,"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/internlm-xcomposer-2-5-a-versatile-large#ran","syntology_url":"https://syntology.ai/paper/2407.03320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03320"}},"official":{"repos":["internlm/internlm-xcomposer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/a-bounding-box-is-worth-one-token","slug":"a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","arxiv_id":"2407.01976","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bounding-box-is-worth-one-token#ran","syntology_url":"https://syntology.ai/paper/2407.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01976"}},"official":{"repos":["laytextllm/laytextllm"],"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/helpful-assistant-or-fruitful-facilitator","slug":"helpful-assistant-or-fruitful-facilitator","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","date":"2024-07-02","arxiv_id":"2407.02099","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"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, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/helpful-assistant-or-fruitful-facilitator#ran","syntology_url":"https://syntology.ai/paper/2407.02099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02099"}},"official":{"repos":["peluz/persona-behavior"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multilingual-trolley-problems-for-language","slug":"multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/multilingual-trolley-problems-for-language#ran","syntology_url":"https://syntology.ai/paper/2407.02273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02273"}},"official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenpacker-efficient-visual-projector-for","slug":"tokenpacker-efficient-visual-projector-for","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","date":"2024-07-02","arxiv_id":"2407.02392","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/tokenpacker-efficient-visual-projector-for#ran","syntology_url":"https://syntology.ai/paper/2407.02392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02392"}},"official":{"repos":["circleradon/tokenpacker"],"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/minference-1-0-accelerating-pre-filling-for","slug":"minference-1-0-accelerating-pre-filling-for","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","date":"2024-07-02","arxiv_id":"2407.02490","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minference-1-0-accelerating-pre-filling-for#ran","syntology_url":"https://syntology.ai/paper/2407.02490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02490"}},"official":{"repos":["microsoft/MInference"],"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":["listed","official"]}}},{"url":"/paper/large-language-models-are-involuntary-truth","slug":"large-language-models-are-involuntary-truth","title":"Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks","date":"2024-07-01","arxiv_id":"2407.00869","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/large-language-models-are-involuntary-truth#ran","syntology_url":"https://syntology.ai/paper/2407.00869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00869"}},"official":{"repos":["Yue-LLM-Pit/FFA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ibsen-director-actor-agent-collaboration-for","slug":"ibsen-director-actor-agent-collaboration-for","title":"IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation","date":"2024-07-01","arxiv_id":"2407.01093","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":0,"n_no_contract":7,"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, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ibsen-director-actor-agent-collaboration-for#ran","syntology_url":"https://syntology.ai/paper/2407.01093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01093"}},"official":{"repos":["OpenDFM/ibsen"],"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/revisiting-random-walks-for-learning-on","slug":"revisiting-random-walks-for-learning-on","title":"Revisiting Random Walks for Learning on Graphs","date":"2024-07-01","arxiv_id":"2407.01214","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/revisiting-random-walks-for-learning-on#ran","syntology_url":"https://syntology.ai/paper/2407.01214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01214"}},"official":{"repos":["jw9730/random-walk"],"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/tree-search-for-language-model-agents","slug":"tree-search-for-language-model-agents","title":"Tree Search for Language Model Agents","date":"2024-07-01","arxiv_id":"2407.01476","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"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, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tree-search-for-language-model-agents#ran","syntology_url":"https://syntology.ai/paper/2407.01476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01476"}},"official":null}},{"url":"/paper/regmix-data-mixture-as-regression-for","slug":"regmix-data-mixture-as-regression-for","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","date":"2024-07-01","arxiv_id":"2407.01492","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/regmix-data-mixture-as-regression-for#ran","syntology_url":"https://syntology.ai/paper/2407.01492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01492"}},"official":{"repos":["sail-sg/regmix"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/crab-cross-environment-agent-benchmark-for","slug":"crab-cross-environment-agent-benchmark-for","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","date":"2024-07-01","arxiv_id":"2407.01511","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/crab-cross-environment-agent-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.01511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01511"}},"official":{"repos":["camel-ai/crab"],"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/meerkat-audio-visual-large-language-model-for","slug":"meerkat-audio-visual-large-language-model-for","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","date":"2024-07-01","arxiv_id":"2407.01851","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/meerkat-audio-visual-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2407.01851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01851"}},"official":{"repos":["schowdhury671/meerkat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/autoflow-automated-workflow-generation-for","slug":"autoflow-automated-workflow-generation-for","title":"AutoFlow: Automated Workflow Generation for Large Language Model Agents","date":"2024-07-01","arxiv_id":"2407.12821","repositories_listed":1,"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/autoflow-automated-workflow-generation-for#ran","syntology_url":"https://syntology.ai/paper/2407.12821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12821"}},"official":{"repos":["agiresearch/autoflow"],"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/learning-formal-mathematics-from-intrinsic","slug":"learning-formal-mathematics-from-intrinsic","title":"Learning Formal Mathematics From Intrinsic Motivation","date":"2024-06-30","arxiv_id":"2407.00695","repositories_listed":2,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/learning-formal-mathematics-from-intrinsic#ran","syntology_url":"https://syntology.ai/paper/2407.00695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00695"}},"official":{"repos":["gpoesia/minimo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/yulan-an-open-source-large-language-model","slug":"yulan-an-open-source-large-language-model","title":"YuLan: An Open-source Large Language Model","date":"2024-06-28","arxiv_id":"2406.19853","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/yulan-an-open-source-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.19853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19853"}},"official":{"repos":["ruc-gsai/yulan-chat"],"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/evf-sam-early-vision-language-fusion-for-text","slug":"evf-sam-early-vision-language-fusion-for-text","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","date":"2024-06-28","arxiv_id":"2406.20076","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":2,"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/evf-sam-early-vision-language-fusion-for-text#ran","syntology_url":"https://syntology.ai/paper/2406.20076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20076"}},"official":{"repos":["hustvl/evf-sam"],"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","unlocated"]}}},{"url":"/paper/scaling-synthetic-data-creation-with","slug":"scaling-synthetic-data-creation-with","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","date":"2024-06-28","arxiv_id":"2406.20094","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/scaling-synthetic-data-creation-with#ran","syntology_url":"https://syntology.ai/paper/2406.20094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20094"}},"official":{"repos":["tencent-ailab/persona-hub"],"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/decoding-time-language-model-alignment-with","slug":"decoding-time-language-model-alignment-with","title":"Decoding-Time Language Model Alignment with Multiple Objectives","date":"2024-06-27","arxiv_id":"2406.18853","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/decoding-time-language-model-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2406.18853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18853"}},"official":{"repos":["srzer/mod"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficacy-of-language-model-self-play-in-non","slug":"efficacy-of-language-model-self-play-in-non","title":"Efficacy of Language Model Self-Play in Non-Zero-Sum Games","date":"2024-06-27","arxiv_id":"2406.18872","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/efficacy-of-language-model-self-play-in-non#ran","syntology_url":"https://syntology.ai/paper/2406.18872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18872"}},"official":{"repos":["nickatomlin/lm-selfplay"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robouniview-visual-language-model-with","slug":"robouniview-visual-language-model-with","title":"RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation","date":"2024-06-27","arxiv_id":"2406.18977","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/robouniview-visual-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2406.18977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18977"}},"official":{"repos":["liufanfanlff/robouniview"],"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/a-refer-and-ground-multimodal-large-language","slug":"a-refer-and-ground-multimodal-large-language","title":"A Refer-and-Ground Multimodal Large Language Model for Biomedicine","date":"2024-06-26","arxiv_id":"2406.18146","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/a-refer-and-ground-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.18146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18146"}},"official":{"repos":["shawnhuang497/bird"],"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/themis-towards-flexible-and-interpretable-nlg","slug":"themis-towards-flexible-and-interpretable-nlg","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","date":"2024-06-26","arxiv_id":"2406.18365","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 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/themis-towards-flexible-and-interpretable-nlg#ran","syntology_url":"https://syntology.ai/paper/2406.18365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18365"}},"official":{"repos":["PKU-ONELab/Themis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-we-trust-the-performance-evaluation-of","slug":"can-we-trust-the-performance-evaluation-of","title":"Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?","date":"2024-06-25","arxiv_id":"2406.17274","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":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) · 0 unverified","sample_list":"/paper/can-we-trust-the-performance-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2406.17274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17274"}},"official":{"repos":["he159ok/benchmark-of-uncertainty-estimation-methods-in-text-summarization"],"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/native-design-bias-studying-the-impact-of","slug":"native-design-bias-studying-the-impact-of","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","date":"2024-06-25","arxiv_id":"2406.17385","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"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) · 7 unverified","sample_list":"/paper/native-design-bias-studying-the-impact-of#ran","syntology_url":"https://syntology.ai/paper/2406.17385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17385"}},"official":{"repos":["manon-reusens/native_en_bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/make-some-noise-unlocking-language-model","slug":"make-some-noise-unlocking-language-model","title":"Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training","date":"2024-06-25","arxiv_id":"2406.17404","repositories_listed":1,"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":2,"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/make-some-noise-unlocking-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.17404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17404"}},"official":{"repos":["wyxstriker/MakeSomeNoiseInference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-property-steering-of-large-language","slug":"multi-property-steering-of-large-language","title":"Multi-property Steering of Large Language Models with Dynamic Activation Composition","date":"2024-06-25","arxiv_id":"2406.17563","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":8,"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/multi-property-steering-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.17563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17563"}},"official":{"repos":["danielsc4/dynamic-activation-composition"],"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/varbench-robust-language-model-benchmarking","slug":"varbench-robust-language-model-benchmarking","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","date":"2024-06-25","arxiv_id":"2406.17681","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/varbench-robust-language-model-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.17681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17681"}},"official":{"repos":["qbetterk/VarBench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-distributional-to-overton-pluralism","slug":"from-distributional-to-overton-pluralism","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","date":"2024-06-25","arxiv_id":"2406.17692","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/from-distributional-to-overton-pluralism#ran","syntology_url":"https://syntology.ai/paper/2406.17692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17692"}},"official":{"repos":["thomlake/investigating-alignment"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-alchemist-automated-labeling-500x-cheaper","slug":"the-alchemist-automated-labeling-500x-cheaper","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","date":"2024-06-25","arxiv_id":"2407.11004","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/the-alchemist-automated-labeling-500x-cheaper#ran","syntology_url":"https://syntology.ai/paper/2407.11004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11004"}},"official":{"repos":["sprocketlab/alchemist"],"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/c-llm-learn-to-check-chinese-spelling-errors","slug":"c-llm-learn-to-check-chinese-spelling-errors","title":"C-LLM: Learn to Check Chinese Spelling Errors Character by Character","date":"2024-06-24","arxiv_id":"2406.16536","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/c-llm-learn-to-check-chinese-spelling-errors#ran","syntology_url":"https://syntology.ai/paper/2406.16536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16536"}},"official":{"repos":["ktlktl/c-llm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/finding-transformer-circuits-with-edge","slug":"finding-transformer-circuits-with-edge","title":"Finding Transformer Circuits with Edge Pruning","date":"2024-06-24","arxiv_id":"2406.16778","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finding-transformer-circuits-with-edge#ran","syntology_url":"https://syntology.ai/paper/2406.16778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16778"}},"official":{"repos":["princeton-nlp/edge-pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/res-q-evaluating-code-editing-large-language","slug":"res-q-evaluating-code-editing-large-language","title":"RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale","date":"2024-06-24","arxiv_id":"2406.16801","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/res-q-evaluating-code-editing-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16801"}},"official":{"repos":["qurrent-ai/res-q"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/long-context-transfer-from-language-to-vision","slug":"long-context-transfer-from-language-to-vision","title":"Long Context Transfer from Language to Vision","date":"2024-06-24","arxiv_id":"2406.16852","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-context-transfer-from-language-to-vision#ran","syntology_url":"https://syntology.ai/paper/2406.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16852"}},"official":{"repos":["evolvinglmms-lab/longva"],"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":["listed","official","unlocated"]}}},{"url":"/paper/safely-learning-with-private-data-a-federated","slug":"safely-learning-with-private-data-a-federated","title":"Safely Learning with Private Data: A Federated Learning Framework for Large Language Model","date":"2024-06-21","arxiv_id":"2406.14898","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/safely-learning-with-private-data-a-federated#ran","syntology_url":"https://syntology.ai/paper/2406.14898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14898"}},"official":{"repos":["TAP-LLM/SplitFedLLM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/moa-mixture-of-sparse-attention-for-automatic","slug":"moa-mixture-of-sparse-attention-for-automatic","title":"MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression","date":"2024-06-21","arxiv_id":"2406.14909","repositories_listed":1,"syntology":{"n":22,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moa-mixture-of-sparse-attention-for-automatic#ran","syntology_url":"https://syntology.ai/paper/2406.14909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14909"}},"official":{"repos":["thu-nics/moa"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/autonomous-agents-for-collaborative-task","slug":"autonomous-agents-for-collaborative-task","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","date":"2024-06-21","arxiv_id":"2406.14928","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/autonomous-agents-for-collaborative-task#ran","syntology_url":"https://syntology.ai/paper/2406.14928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14928"}},"official":{"repos":["thinkwee/iAgents"],"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":["official"]}}},{"url":"/paper/first-faster-improved-listwise-reranking-with","slug":"first-faster-improved-listwise-reranking-with","title":"FIRST: Faster Improved Listwise Reranking with Single Token Decoding","date":"2024-06-21","arxiv_id":"2406.15657","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/first-faster-improved-listwise-reranking-with#ran","syntology_url":"https://syntology.ai/paper/2406.15657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15657"}},"official":{"repos":["gangiswag/llm-reranker"],"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/citybench-evaluating-the-capabilities-of","slug":"citybench-evaluating-the-capabilities-of","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","date":"2024-06-20","arxiv_id":"2406.13945","repositories_listed":1,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"17 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/citybench-evaluating-the-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2406.13945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13945"}},"official":{"repos":["tsinghua-fib-lab/citybench"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/livemind-low-latency-large-language-models","slug":"livemind-low-latency-large-language-models","title":"LiveMind: Low-latency Large Language Models with Simultaneous Inference","date":"2024-06-20","arxiv_id":"2406.14319","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/livemind-low-latency-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.14319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14319"}},"official":{"repos":["chuangtaochen-tum/livemind"],"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/revealing-vision-language-integration-in-the","slug":"revealing-vision-language-integration-in-the","title":"Revealing Vision-Language Integration in the Brain with Multimodal Networks","date":"2024-06-20","arxiv_id":"2406.14481","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/revealing-vision-language-integration-in-the#ran","syntology_url":"https://syntology.ai/paper/2406.14481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14481"}},"official":{"repos":["vsubramaniam851/brain-multimodal"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prism-a-framework-for-decoupling-and","slug":"prism-a-framework-for-decoupling-and","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","date":"2024-06-20","arxiv_id":"2406.14544","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prism-a-framework-for-decoupling-and#ran","syntology_url":"https://syntology.ai/paper/2406.14544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14544"}},"official":{"repos":["sparksjoe/prism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/asynchronous-large-language-model-enhanced","slug":"asynchronous-large-language-model-enhanced","title":"Asynchronous Large Language Model Enhanced Planner for Autonomous Driving","date":"2024-06-20","arxiv_id":"2406.14556","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/asynchronous-large-language-model-enhanced#ran","syntology_url":"https://syntology.ai/paper/2406.14556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14556"}},"official":{"repos":["memberre/asyncdriver"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-a-large-language-model-enhanced","slug":"llm-a-large-language-model-enhanced","title":"LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning","date":"2024-06-20","arxiv_id":"2407.02511","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/llm-a-large-language-model-enhanced#ran","syntology_url":"https://syntology.ai/paper/2407.02511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02511"}},"official":{"repos":["SilinMeng0510/llm-astar"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/patholm-identifying-pathogenicity-from-the","slug":"patholm-identifying-pathogenicity-from-the","title":"PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model","date":"2024-06-19","arxiv_id":"2406.13133","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/patholm-identifying-pathogenicity-from-the#ran","syntology_url":"https://syntology.ai/paper/2406.13133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13133"}},"official":{"repos":["Sajib-006/Patho-LM"],"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/encoder-vs-decoder-comparative-analysis-of","slug":"encoder-vs-decoder-comparative-analysis-of","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","date":"2024-06-19","arxiv_id":"2406.13469","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/encoder-vs-decoder-comparative-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2406.13469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13469"}},"official":null}},{"url":"/paper/unveiling-the-hidden-structure-of-self","slug":"unveiling-the-hidden-structure-of-self","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","date":"2024-06-19","arxiv_id":"2406.13762","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/unveiling-the-hidden-structure-of-self#ran","syntology_url":"https://syntology.ai/paper/2406.13762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13762"}},"official":{"repos":["rachtsy/kpca_code"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/elliptical-attention","slug":"elliptical-attention","title":"Elliptical Attention","date":"2024-06-19","arxiv_id":"2406.13770","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/elliptical-attention#ran","syntology_url":"https://syntology.ai/paper/2406.13770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13770"}},"official":{"repos":["stefvk/elliptical-attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/holmes-vad-towards-unbiased-and-explainable","slug":"holmes-vad-towards-unbiased-and-explainable","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","date":"2024-06-18","arxiv_id":"2406.12235","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/holmes-vad-towards-unbiased-and-explainable#ran","syntology_url":"https://syntology.ai/paper/2406.12235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12235"}},"official":{"repos":["pipixin321/holmesvad"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pslm-parallel-generation-of-text-and-speech","slug":"pslm-parallel-generation-of-text-and-speech","title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","date":"2024-06-18","arxiv_id":"2406.12428","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":5,"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/pslm-parallel-generation-of-text-and-speech#ran","syntology_url":"https://syntology.ai/paper/2406.12428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12428"}},"official":{"repos":["eleutherai/gpt-neox"],"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/breaking-the-ceiling-of-the-llm-community-by","slug":"breaking-the-ceiling-of-the-llm-community-by","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","date":"2024-06-18","arxiv_id":"2406.12585","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}},"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/low-redundant-optimization-for-large-language","slug":"low-redundant-optimization-for-large-language","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","date":"2024-06-18","arxiv_id":"2406.12606","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/low-redundant-optimization-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.12606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12606"}},"official":{"repos":["rucaibox/allo"],"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/efficient-and-long-tailed-generalization-for","slug":"efficient-and-long-tailed-generalization-for","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","date":"2024-06-18","arxiv_id":"2406.12638","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-and-long-tailed-generalization-for#ran","syntology_url":"https://syntology.ai/paper/2406.12638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12638"}},"official":{"repos":["shijxcs/candle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/magic-generating-self-correction-guideline","slug":"magic-generating-self-correction-guideline","title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","date":"2024-06-18","arxiv_id":"2406.12692","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/magic-generating-self-correction-guideline#ran","syntology_url":"https://syntology.ai/paper/2406.12692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12692"}},"official":{"repos":["microsoft/synqo"],"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/agentreview-exploring-peer-review-dynamics","slug":"agentreview-exploring-peer-review-dynamics","title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","date":"2024-06-18","arxiv_id":"2406.12708","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/agentreview-exploring-peer-review-dynamics#ran","syntology_url":"https://syntology.ai/paper/2406.12708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12708"}},"official":{"repos":["ahren09/agentreview"],"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/bioscan-5m-a-multimodal-dataset-for-insect","slug":"bioscan-5m-a-multimodal-dataset-for-insect","title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","date":"2024-06-18","arxiv_id":"2406.12723","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/bioscan-5m-a-multimodal-dataset-for-insect#ran","syntology_url":"https://syntology.ai/paper/2406.12723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12723"}},"official":{"repos":["bioscan-ml/dataset"],"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":["named_in_paper","official"]}}},{"url":"/paper/interpretable-preferences-via-multi-objective","slug":"interpretable-preferences-via-multi-objective","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","date":"2024-06-18","arxiv_id":"2406.12845","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-preferences-via-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.12845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12845"}},"official":{"repos":["RLHFlow/RLHF-Reward-Modeling"],"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/moleculargpt-open-large-language-model-llm","slug":"moleculargpt-open-large-language-model-llm","title":"MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction","date":"2024-06-18","arxiv_id":"2406.12950","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/moleculargpt-open-large-language-model-llm#ran","syntology_url":"https://syntology.ai/paper/2406.12950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12950"}},"official":{"repos":["nyushcs/moleculargpt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2406-15487","slug":"2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","date":"2024-06-18","arxiv_id":"2406.15487","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2406-15487#ran","syntology_url":"https://syntology.ai/paper/2406.15487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15487"}},"official":null}},{"url":"/paper/sugarcrepe-dataset-vision-language-model","slug":"sugarcrepe-dataset-vision-language-model","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","date":"2024-06-17","arxiv_id":"2406.11171","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sugarcrepe-dataset-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11171"}},"official":{"repos":["Sri-Harsha/scpp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/watch-every-step-llm-agent-learning-via","slug":"watch-every-step-llm-agent-learning-via","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","date":"2024-06-17","arxiv_id":"2406.11176","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/watch-every-step-llm-agent-learning-via#ran","syntology_url":"https://syntology.ai/paper/2406.11176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11176"}},"official":{"repos":["weiminxiong/ipr"],"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/avatar-optimizing-llm-agents-for-tool","slug":"avatar-optimizing-llm-agents-for-tool","title":"AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning","date":"2024-06-17","arxiv_id":"2406.11200","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/avatar-optimizing-llm-agents-for-tool#ran","syntology_url":"https://syntology.ai/paper/2406.11200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11200"}},"official":{"repos":["zou-group/avatar"],"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/i-srt-aligning-large-multimodal-models-for","slug":"i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","arxiv_id":"2406.11280","repositories_listed":4,"syntology":{"n":30,"n_ran":26,"n_constructed":0,"n_ran_checked":18,"n_instrument":8,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":16,"n_pointer_only":15,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 2 violated, 16 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/i-srt-aligning-large-multimodal-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.11280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11280"}},"official":{"repos":["snumprlab/SRT","snumprlab/isr-dpo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fairer-preferences-elicit-improved-human","slug":"fairer-preferences-elicit-improved-human","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","date":"2024-06-17","arxiv_id":"2406.11370","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":4,"n_ran_checked":10,"n_instrument":10,"n_unverified":9,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":2,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/fairer-preferences-elicit-improved-human#ran","syntology_url":"https://syntology.ai/paper/2406.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11370"}},"official":{"repos":["cambridgeltl/zepo"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-simple-and-effective-l-2-norm-based","slug":"a-simple-and-effective-l-2-norm-based","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","date":"2024-06-17","arxiv_id":"2406.11430","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":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/a-simple-and-effective-l-2-norm-based#ran","syntology_url":"https://syntology.ai/paper/2406.11430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11430"}},"official":{"repos":["alessiodevoto/l2compress"],"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/datacomp-lm-in-search-of-the-next-generation","slug":"datacomp-lm-in-search-of-the-next-generation","title":"DataComp-LM: In search of the next generation of training sets for language models","date":"2024-06-17","arxiv_id":"2406.11794","repositories_listed":3,"syntology":{"n":22,"n_ran":22,"n_constructed":0,"n_ran_checked":20,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":1,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/datacomp-lm-in-search-of-the-next-generation#ran","syntology_url":"https://syntology.ai/paper/2406.11794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11794"}},"official":null}},{"url":"/paper/language-modeling-with-editable-external","slug":"language-modeling-with-editable-external","title":"Language Modeling with Editable External Knowledge","date":"2024-06-17","arxiv_id":"2406.11830","repositories_listed":1,"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":2,"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/language-modeling-with-editable-external#ran","syntology_url":"https://syntology.ai/paper/2406.11830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11830"}},"official":{"repos":["belindal/erase"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-encoder-free-vision-language-models","slug":"unveiling-encoder-free-vision-language-models","title":"Unveiling Encoder-Free Vision-Language Models","date":"2024-06-17","arxiv_id":"2406.11832","repositories_listed":1,"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":3,"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/unveiling-encoder-free-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.11832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11832"}},"official":{"repos":["baaivision/eve"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/mdpo-conditional-preference-optimization-for","slug":"mdpo-conditional-preference-optimization-for","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11839","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mdpo-conditional-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2406.11839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11839"}},"official":{"repos":["luka-group/mDPO"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dialogue-action-tokens-steering-language","slug":"dialogue-action-tokens-steering-language","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","date":"2024-06-17","arxiv_id":"2406.11978","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"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, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dialogue-action-tokens-steering-language#ran","syntology_url":"https://syntology.ai/paper/2406.11978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11978"}},"official":{"repos":["likenneth/dialogue_action_token"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fintruthqa-a-benchmark-dataset-for-evaluating","slug":"fintruthqa-a-benchmark-dataset-for-evaluating","title":"FinTruthQA: A Benchmark Dataset for Evaluating the Quality of Financial Information Disclosure","date":"2024-06-17","arxiv_id":"2406.12009","repositories_listed":1,"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/fintruthqa-a-benchmark-dataset-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2406.12009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12009"}},"official":{"repos":["bethxx99/FinTruthQA"],"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/citrus-chunked-instruction-aware-state","slug":"citrus-chunked-instruction-aware-state","title":"CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling","date":"2024-06-17","arxiv_id":"2406.12018","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"phrase":"5 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; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/citrus-chunked-instruction-aware-state#ran","syntology_url":"https://syntology.ai/paper/2406.12018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12018"}},"official":{"repos":["ybai-nlp/CItruS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/spa-vl-a-comprehensive-safety-preference","slug":"spa-vl-a-comprehensive-safety-preference","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","date":"2024-06-17","arxiv_id":"2406.12030","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spa-vl-a-comprehensive-safety-preference#ran","syntology_url":"https://syntology.ai/paper/2406.12030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12030"}},"official":{"repos":["echosechen/spa-vl-rlhf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"e5d1146f5a4bb37d03aba0d2fb8eced95b7b0c4377949bd886c138ff407ea45a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}