{"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/large-language-model/papers/ran/4","list_of":"/task/large-language-model","task":"Large Language Model","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":4,"pages_in_order":9,"rows_per_page":100,"rows":[301,400],"of":801,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/large-language-model/papers/ran/1","prev":"/task/large-language-model/papers/ran/3","next":"/task/large-language-model/papers/ran/5","papers":[{"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/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/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/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/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/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/large-scale-transfer-learning-for-tabular","slug":"large-scale-transfer-learning-for-tabular","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","date":"2024-06-17","arxiv_id":"2406.12031","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-scale-transfer-learning-for-tabular#ran","syntology_url":"https://syntology.ai/paper/2406.12031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12031"}},"official":{"repos":["mlfoundations/rtfm","mlfoundations/tabliblib"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sharelora-parameter-efficient-and-robust","slug":"sharelora-parameter-efficient-and-robust","title":"ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.10785","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/sharelora-parameter-efficient-and-robust#ran","syntology_url":"https://syntology.ai/paper/2406.10785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10785"}},"official":{"repos":["Rain9876/ShareLoRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/avoiding-copyright-infringement-via-machine","slug":"avoiding-copyright-infringement-via-machine","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","date":"2024-06-16","arxiv_id":"2406.10952","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/avoiding-copyright-infringement-via-machine#ran","syntology_url":"https://syntology.ai/paper/2406.10952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10952"}},"official":{"repos":["guangyaodou/SSU_Unlearn"],"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/large-language-model-validity-via-enhanced","slug":"large-language-model-validity-via-enhanced","title":"Large language model validity via enhanced conformal prediction methods","date":"2024-06-14","arxiv_id":"2406.09714","repositories_listed":3,"syntology":{"n":32,"n_ran":23,"n_constructed":0,"n_ran_checked":22,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":22,"n_pointer_only":12,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/large-language-model-validity-via-enhanced#ran","syntology_url":"https://syntology.ai/paper/2406.09714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09714"}},"official":{"repos":["jjcherian/conformal-safety"],"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":["found_in_text","listed","official"]}}},{"url":"/paper/streambench-towards-benchmarking-continuous","slug":"streambench-towards-benchmarking-continuous","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","date":"2024-06-13","arxiv_id":"2406.08747","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/streambench-towards-benchmarking-continuous#ran","syntology_url":"https://syntology.ai/paper/2406.08747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08747"}},"official":{"repos":["stream-bench/stream-bench"],"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/large-language-model-unlearning-via-embedding","slug":"large-language-model-unlearning-via-embedding","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","date":"2024-06-12","arxiv_id":"2406.07933","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/large-language-model-unlearning-via-embedding#ran","syntology_url":"https://syntology.ai/paper/2406.07933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07933"}},"official":{"repos":["chrisliu298/llm-unlearn-eco"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/dataset-and-lessons-learned-from-the-2024","slug":"dataset-and-lessons-learned-from-the-2024","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","date":"2024-06-12","arxiv_id":"2406.07954","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/dataset-and-lessons-learned-from-the-2024#ran","syntology_url":"https://syntology.ai/paper/2406.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07954"}},"official":{"repos":["ethz-spylab/ctf-satml24-data-analysis"],"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/multimodal-table-understanding","slug":"multimodal-table-understanding","title":"Multimodal Table Understanding","date":"2024-06-12","arxiv_id":"2406.08100","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multimodal-table-understanding#ran","syntology_url":"https://syntology.ai/paper/2406.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08100"}},"official":{"repos":["spursgozmy/table-llava"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/conme-rethinking-evaluation-of-compositional","slug":"conme-rethinking-evaluation-of-compositional","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","date":"2024-06-12","arxiv_id":"2406.08164","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conme-rethinking-evaluation-of-compositional#ran","syntology_url":"https://syntology.ai/paper/2406.08164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08164"}},"official":{"repos":["jmiemirza/conme"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-preference-optimization","slug":"discovering-preference-optimization","title":"Discovering Preference Optimization Algorithms with and for Large Language Models","date":"2024-06-12","arxiv_id":"2406.08414","repositories_listed":3,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/discovering-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2406.08414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08414"}},"official":{"repos":["luchris429/DiscoPOP","samholt/DiscoPOP","vanderschaarlab/discopop"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rs-agent-automating-remote-sensing-tasks","slug":"rs-agent-automating-remote-sensing-tasks","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","date":"2024-06-11","arxiv_id":"2406.07089","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rs-agent-automating-remote-sensing-tasks#ran","syntology_url":"https://syntology.ai/paper/2406.07089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07089"}},"official":{"repos":["intellisensing/rs-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/powerinfer-2-fast-large-language-model","slug":"powerinfer-2-fast-large-language-model","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","date":"2024-06-10","arxiv_id":"2406.06282","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":2,"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/powerinfer-2-fast-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.06282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06282"}},"official":null}},{"url":"/paper/a-fine-tuning-dataset-and-benchmark-for-large","slug":"a-fine-tuning-dataset-and-benchmark-for-large","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","date":"2024-06-08","arxiv_id":"2406.05540","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":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) · 1 unverified","sample_list":"/paper/a-fine-tuning-dataset-and-benchmark-for-large#ran","syntology_url":"https://syntology.ai/paper/2406.05540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05540"}},"official":{"repos":["tsynbio/proteinlmdataset"],"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/locllm-exploiting-generalizable-human","slug":"locllm-exploiting-generalizable-human","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","date":"2024-06-07","arxiv_id":"2406.04659","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/locllm-exploiting-generalizable-human#ran","syntology_url":"https://syntology.ai/paper/2406.04659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04659"}},"official":{"repos":["kennethwdk/LocLLM"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-agents-enhances-large-language","slug":"mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","arxiv_id":"2406.04692","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mixture-of-agents-enhances-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04692"}},"official":null}},{"url":"/paper/crag-comprehensive-rag-benchmark","slug":"crag-comprehensive-rag-benchmark","title":"CRAG -- Comprehensive RAG Benchmark","date":"2024-06-07","arxiv_id":"2406.04744","repositories_listed":2,"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":4,"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/crag-comprehensive-rag-benchmark#ran","syntology_url":"https://syntology.ai/paper/2406.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04744"}},"official":{"repos":["facebookresearch/crag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tool-planner-dynamic-solution-tree-planning","slug":"tool-planner-dynamic-solution-tree-planning","title":"Tool-Planner: Task Planning with Clusters across Multiple Tools","date":"2024-06-06","arxiv_id":"2406.03807","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":1,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tool-planner-dynamic-solution-tree-planning#ran","syntology_url":"https://syntology.ai/paper/2406.03807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03807"}},"official":{"repos":["OceannTwT/Tool-Planner"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/jailbreak-vision-language-models-via-bi-modal","slug":"jailbreak-vision-language-models-via-bi-modal","title":"Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt","date":"2024-06-06","arxiv_id":"2406.04031","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/jailbreak-vision-language-models-via-bi-modal#ran","syntology_url":"https://syntology.ai/paper/2406.04031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04031"}},"official":{"repos":["NY1024/BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt"],"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/posterllava-constructing-a-unified-multi","slug":"posterllava-constructing-a-unified-multi","title":"PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM","date":"2024-06-05","arxiv_id":"2406.02884","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/posterllava-constructing-a-unified-multi#ran","syntology_url":"https://syntology.ai/paper/2406.02884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02884"}},"official":{"repos":["posterllava/posterllava"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-text-cross-alignment-refining-the","slug":"visual-text-cross-alignment-refining-the","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","date":"2024-06-05","arxiv_id":"2406.02915","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":0,"n_instrument":8,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"8 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; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visual-text-cross-alignment-refining-the#ran","syntology_url":"https://syntology.ai/paper/2406.02915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02915"}},"official":{"repos":["tmlr-group/wca"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-text-training-language-models-on-private","slug":"pre-text-training-language-models-on-private","title":"PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs","date":"2024-06-05","arxiv_id":"2406.02958","repositories_listed":1,"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/pre-text-training-language-models-on-private#ran","syntology_url":"https://syntology.ai/paper/2406.02958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02958"}},"official":{"repos":["houcharlie/pre-text"],"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/ranking-manipulation-for-conversational","slug":"ranking-manipulation-for-conversational","title":"Ranking Manipulation for Conversational Search Engines","date":"2024-06-05","arxiv_id":"2406.03589","repositories_listed":4,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ranking-manipulation-for-conversational#ran","syntology_url":"https://syntology.ai/paper/2406.03589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03589"}},"official":{"repos":["spfrommer/ragdoll-data-pipeline","spfrommer/ranking_manipulation","spfrommer/ranking_manipulation_data_pipeline","spfrommer/cse-ranking-manipulation"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/randomized-geometric-algebra-methods-for","slug":"randomized-geometric-algebra-methods-for","title":"Randomized Geometric Algebra Methods for Convex Neural Networks","date":"2024-06-04","arxiv_id":"2406.02806","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/randomized-geometric-algebra-methods-for#ran","syntology_url":"https://syntology.ai/paper/2406.02806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02806"}},"official":{"repos":["pilancilab/Randomized-Geometric-Algebra-Methods-for-Convex-Neural-Networks"],"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/the-geometry-of-categorical-and-hierarchical","slug":"the-geometry-of-categorical-and-hierarchical","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","date":"2024-06-03","arxiv_id":"2406.01506","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/the-geometry-of-categorical-and-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2406.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01506"}},"official":{"repos":["kihopark/llm_categorical_hierarchical_representations"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/helix-distributed-serving-of-large-language","slug":"helix-distributed-serving-of-large-language","title":"Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow","date":"2024-06-03","arxiv_id":"2406.01566","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/helix-distributed-serving-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.01566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01566"}},"official":{"repos":["Thesys-lab/Helix-ASPLOS25"],"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/skywork-moe-a-deep-dive-into-training","slug":"skywork-moe-a-deep-dive-into-training","title":"Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models","date":"2024-06-03","arxiv_id":"2406.06563","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skywork-moe-a-deep-dive-into-training#ran","syntology_url":"https://syntology.ai/paper/2406.06563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06563"}},"official":null}},{"url":"/paper/inverse-constitutional-ai-compressing","slug":"inverse-constitutional-ai-compressing","title":"Inverse Constitutional AI: Compressing Preferences into Principles","date":"2024-06-02","arxiv_id":"2406.06560","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/inverse-constitutional-ai-compressing#ran","syntology_url":"https://syntology.ai/paper/2406.06560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06560"}},"official":{"repos":["rdnfn/icai"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-best-of-both-worlds-toward-an-honest-and","slug":"the-best-of-both-worlds-toward-an-honest-and","title":"HonestLLM: Toward an Honest and Helpful Large Language Model","date":"2024-06-01","arxiv_id":"2406.00380","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/the-best-of-both-worlds-toward-an-honest-and#ran","syntology_url":"https://syntology.ai/paper/2406.00380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00380"}},"official":{"repos":["Flossiee/HonestyLLM"],"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/interpretabnet-distilling-predictive-signals","slug":"interpretabnet-distilling-predictive-signals","title":"InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation","date":"2024-06-01","arxiv_id":"2406.00426","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":10,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 10 samples that ran constructed an object rather than computing a result","sample_list":"/paper/interpretabnet-distilling-predictive-signals#ran","syntology_url":"https://syntology.ai/paper/2406.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00426"}},"official":{"repos":["jacobyhsi/InterpreTabNet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":10,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/meshxl-neural-coordinate-field-for-generative","slug":"meshxl-neural-coordinate-field-for-generative","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","date":"2024-05-31","arxiv_id":"2405.20853","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/meshxl-neural-coordinate-field-for-generative#ran","syntology_url":"https://syntology.ai/paper/2405.20853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20853"}},"official":{"repos":["openmeshlab/meshxl"],"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/query2cad-generating-cad-models-using-natural","slug":"query2cad-generating-cad-models-using-natural","title":"Query2CAD: Generating CAD models using natural language queries","date":"2024-05-31","arxiv_id":"2406.00144","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"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) · 2 unverified","sample_list":"/paper/query2cad-generating-cad-models-using-natural#ran","syntology_url":"https://syntology.ai/paper/2406.00144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00144"}},"official":{"repos":["akshay140601/query2cad"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llamea-a-large-language-model-evolutionary","slug":"llamea-a-large-language-model-evolutionary","title":"LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics","date":"2024-05-30","arxiv_id":"2405.20132","repositories_listed":2,"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/llamea-a-large-language-model-evolutionary#ran","syntology_url":"https://syntology.ai/paper/2405.20132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20132"}},"official":{"repos":["nikivanstein/LLaMEA"],"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":["listed","official"]}}},{"url":"/paper/gnn-rag-graph-neural-retrieval-for-large","slug":"gnn-rag-graph-neural-retrieval-for-large","title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","date":"2024-05-30","arxiv_id":"2405.20139","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/gnn-rag-graph-neural-retrieval-for-large#ran","syntology_url":"https://syntology.ai/paper/2405.20139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20139"}},"official":{"repos":["cmavro/gnn-rag"],"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/evaluating-large-language-model-biases-in","slug":"evaluating-large-language-model-biases-in","title":"Evaluating Large Language Model Biases in Persona-Steered Generation","date":"2024-05-30","arxiv_id":"2405.20253","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evaluating-large-language-model-biases-in#ran","syntology_url":"https://syntology.ai/paper/2405.20253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20253"}},"official":{"repos":["andyjliu/persona-steered-generation-bias"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-augmented-se-3-flow-matching-for","slug":"sequence-augmented-se-3-flow-matching-for","title":"Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation","date":"2024-05-30","arxiv_id":"2405.20313","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":15,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":20,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sequence-augmented-se-3-flow-matching-for#ran","syntology_url":"https://syntology.ai/paper/2405.20313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20313"}},"official":{"repos":["dreamfold/foldflow"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["community","official"]}}},{"url":"/paper/weak-to-strong-search-align-large-language","slug":"weak-to-strong-search-align-large-language","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","date":"2024-05-29","arxiv_id":"2405.19262","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/weak-to-strong-search-align-large-language#ran","syntology_url":"https://syntology.ai/paper/2405.19262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19262"}},"official":{"repos":["zhziszz/weak-to-strong-search"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/map-neo-highly-capable-and-transparent","slug":"map-neo-highly-capable-and-transparent","title":"MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series","date":"2024-05-29","arxiv_id":"2405.19327","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/map-neo-highly-capable-and-transparent#ran","syntology_url":"https://syntology.ai/paper/2405.19327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19327"}},"official":{"repos":["multimodal-art-projection/map-neo"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-in-conversation-team-building-for","slug":"adaptive-in-conversation-team-building-for","title":"Adaptive In-conversation Team Building for Language Model Agents","date":"2024-05-29","arxiv_id":"2405.19425","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/adaptive-in-conversation-team-building-for#ran","syntology_url":"https://syntology.ai/paper/2405.19425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19425"}},"official":{"repos":["ag2ai/ag2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/conveyor-efficient-tool-aware-llm-serving","slug":"conveyor-efficient-tool-aware-llm-serving","title":"Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution","date":"2024-05-29","arxiv_id":"2406.00059","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conveyor-efficient-tool-aware-llm-serving#ran","syntology_url":"https://syntology.ai/paper/2406.00059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00059"}},"official":{"repos":["conveyor-sys/conveyor"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-to-thousands-of-preferences-via","slug":"aligning-to-thousands-of-preferences-via","title":"Aligning to Thousands of Preferences via System Message Generalization","date":"2024-05-28","arxiv_id":"2405.17977","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-to-thousands-of-preferences-via#ran","syntology_url":"https://syntology.ai/paper/2405.17977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17977"}},"official":{"repos":["kaistAI/Janus"],"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":["community","official"]}}},{"url":"/paper/atm-adversarial-tuning-multi-agent-system","slug":"atm-adversarial-tuning-multi-agent-system","title":"ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator","date":"2024-05-28","arxiv_id":"2405.18111","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"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) · 4 unverified","sample_list":"/paper/atm-adversarial-tuning-multi-agent-system#ran","syntology_url":"https://syntology.ai/paper/2405.18111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18111"}},"official":{"repos":["chuhac/atm-rag"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/chess-contextual-harnessing-for-efficient-sql","slug":"chess-contextual-harnessing-for-efficient-sql","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","date":"2024-05-27","arxiv_id":"2405.16755","repositories_listed":2,"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/chess-contextual-harnessing-for-efficient-sql#ran","syntology_url":"https://syntology.ai/paper/2405.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16755"}},"official":{"repos":["shayantalaei/chess"],"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/reason3d-searching-and-reasoning-3d","slug":"reason3d-searching-and-reasoning-3d","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","date":"2024-05-27","arxiv_id":"2405.17427","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"5 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reason3d-searching-and-reasoning-3d#ran","syntology_url":"https://syntology.ai/paper/2405.17427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17427"}},"official":{"repos":["kuanchihhuang/reason3d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/intruding-with-words-towards-understanding","slug":"intruding-with-words-towards-understanding","title":"Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level","date":"2024-05-26","arxiv_id":"2405.16405","repositories_listed":1,"syntology":{"n":24,"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":24,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/intruding-with-words-towards-understanding#ran","syntology_url":"https://syntology.ai/paper/2405.16405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16405"}},"official":{"repos":["leirunlin/text-level-graph-attack"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/cacheblend-fast-large-language-model-serving","slug":"cacheblend-fast-large-language-model-serving","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","date":"2024-05-26","arxiv_id":"2405.16444","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"10 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cacheblend-fast-large-language-model-serving#ran","syntology_url":"https://syntology.ai/paper/2405.16444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16444"}},"official":{"repos":["YaoJiayi/CacheBlend"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-gpt-an-advanced-multimodal-multitask","slug":"m-3-gpt-an-advanced-multimodal-multitask","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","date":"2024-05-25","arxiv_id":"2405.16273","repositories_listed":1,"syntology":{"n":25,"n_ran":17,"n_constructed":4,"n_ran_checked":15,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":25,"phrase":"17 ran (of which 4 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/m-3-gpt-an-advanced-multimodal-multitask#ran","syntology_url":"https://syntology.ai/paper/2405.16273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16273"}},"official":{"repos":["luomingshuang/m3gpt"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":4,"n_ran_no_instrument_failure":15,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-code-world-models-with-large","slug":"generating-code-world-models-with-large","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","date":"2024-05-24","arxiv_id":"2405.15383","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generating-code-world-models-with-large#ran","syntology_url":"https://syntology.ai/paper/2405.15383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15383"}},"official":{"repos":["nicoladainese96/code-world-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synergizing-in-context-learning-with-hints","slug":"synergizing-in-context-learning-with-hints","title":"Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems","date":"2024-05-24","arxiv_id":"2405.15585","repositories_listed":0,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/synergizing-in-context-learning-with-hints#ran","syntology_url":"https://syntology.ai/paper/2405.15585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15585"}},"official":null}},{"url":"/paper/lm4lv-a-frozen-large-language-model-for-low","slug":"lm4lv-a-frozen-large-language-model-for-low","title":"LM4LV: A Frozen Large Language Model for Low-level Vision Tasks","date":"2024-05-24","arxiv_id":"2405.15734","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":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lm4lv-a-frozen-large-language-model-for-low#ran","syntology_url":"https://syntology.ai/paper/2405.15734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15734"}},"official":{"repos":["bytetriper/lm4lv"],"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/achieving-dimension-free-communication-in","slug":"achieving-dimension-free-communication-in","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","date":"2024-05-24","arxiv_id":"2405.15861","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/achieving-dimension-free-communication-in#ran","syntology_url":"https://syntology.ai/paper/2405.15861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15861"}},"official":{"repos":["ZidongLiu/DeComFL"],"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/art-automatic-red-teaming-for-text-to-image","slug":"art-automatic-red-teaming-for-text-to-image","title":"ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users","date":"2024-05-24","arxiv_id":"2405.19360","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/art-automatic-red-teaming-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2405.19360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19360"}},"official":{"repos":["guanlinlee/art"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-can-be-zero-shot","slug":"large-language-models-can-be-zero-shot","title":"Large language models can be zero-shot anomaly detectors for time series?","date":"2024-05-23","arxiv_id":"2405.14755","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/large-language-models-can-be-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2405.14755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14755"}},"official":{"repos":["sintel-dev/sigllm"],"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/adapting-multi-modal-large-language-model-to","slug":"adapting-multi-modal-large-language-model-to","title":"Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards","date":"2024-05-22","arxiv_id":"2405.13459","repositories_listed":0,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/adapting-multi-modal-large-language-model-to#ran","syntology_url":"https://syntology.ai/paper/2405.13459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13459"}},"official":null}},{"url":"/paper/chatscene-knowledge-enabled-safety-critical","slug":"chatscene-knowledge-enabled-safety-critical","title":"ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles","date":"2024-05-22","arxiv_id":"2405.14062","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/chatscene-knowledge-enabled-safety-critical#ran","syntology_url":"https://syntology.ai/paper/2405.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14062"}},"official":{"repos":["javyduck/ChatScene"],"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/token-wise-influential-training-data","slug":"token-wise-influential-training-data","title":"Token-wise Influential Training Data Retrieval for Large Language Models","date":"2024-05-20","arxiv_id":"2405.11724","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"5 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/token-wise-influential-training-data#ran","syntology_url":"https://syntology.ai/paper/2405.11724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11724"}},"official":{"repos":["huawei-lin/rapidin"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/can-ai-relate-testing-large-language-model","slug":"can-ai-relate-testing-large-language-model","title":"Can AI Relate: Testing Large Language Model Response for Mental Health Support","date":"2024-05-20","arxiv_id":"2405.12021","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-ai-relate-testing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2405.12021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12021"}},"official":{"repos":["skgabriel/mh-eval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-modular-llms-by-building-and-reusing","slug":"towards-modular-llms-by-building-and-reusing","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","date":"2024-05-18","arxiv_id":"2405.11157","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-modular-llms-by-building-and-reusing#ran","syntology_url":"https://syntology.ai/paper/2405.11157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11157"}},"official":null}},{"url":"/paper/rdrec-rationale-distillation-for-llm-based","slug":"rdrec-rationale-distillation-for-llm-based","title":"RDRec: Rationale Distillation for LLM-based Recommendation","date":"2024-05-17","arxiv_id":"2405.10587","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rdrec-rationale-distillation-for-llm-based#ran","syntology_url":"https://syntology.ai/paper/2405.10587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10587"}},"official":{"repos":["wangxfng/rdrec"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/libra-building-decoupled-vision-system-on","slug":"libra-building-decoupled-vision-system-on","title":"Libra: Building Decoupled Vision System on Large Language Models","date":"2024-05-16","arxiv_id":"2405.10140","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/libra-building-decoupled-vision-system-on#ran","syntology_url":"https://syntology.ai/paper/2405.10140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10140"}},"official":{"repos":["yifanxu74/libra"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/keep-it-private-unsupervised-privatization-of","slug":"keep-it-private-unsupervised-privatization-of","title":"Keep It Private: Unsupervised Privatization of Online Text","date":"2024-05-16","arxiv_id":"2405.10260","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":10,"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/keep-it-private-unsupervised-privatization-of#ran","syntology_url":"https://syntology.ai/paper/2405.10260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10260"}},"official":{"repos":["csbao/kip-privatization"],"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/4d-panoptic-scene-graph-generation-1","slug":"4d-panoptic-scene-graph-generation-1","title":"4D Panoptic Scene Graph Generation","date":"2024-05-16","arxiv_id":"2405.10305","repositories_listed":3,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/4d-panoptic-scene-graph-generation-1#ran","syntology_url":"https://syntology.ai/paper/2405.10305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10305"}},"official":{"repos":["jingkang50/psg4d","Jingkang50/OpenPSG","jingkang50/openpvsg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spectral-editing-of-activations-for-large","slug":"spectral-editing-of-activations-for-large","title":"Spectral Editing of Activations for Large Language Model Alignment","date":"2024-05-15","arxiv_id":"2405.09719","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spectral-editing-of-activations-for-large#ran","syntology_url":"https://syntology.ai/paper/2405.09719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09719"}},"official":{"repos":["yfqiu-nlp/sea-llm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hunyuan-dit-a-powerful-multi-resolution","slug":"hunyuan-dit-a-powerful-multi-resolution","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","date":"2024-05-14","arxiv_id":"2405.08748","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hunyuan-dit-a-powerful-multi-resolution#ran","syntology_url":"https://syntology.ai/paper/2405.08748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.08748"}},"official":{"repos":["tencent/hunyuandit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/harnessing-the-power-of-mllms-for","slug":"harnessing-the-power-of-mllms-for","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","date":"2024-05-08","arxiv_id":"2405.04940","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"9 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-mllms-for#ran","syntology_url":"https://syntology.ai/paper/2405.04940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04940"}},"official":{"repos":["wentaotan/mllm4text-reid"],"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/fishing-for-magikarp-automatically-detecting","slug":"fishing-for-magikarp-automatically-detecting","title":"Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models","date":"2024-05-08","arxiv_id":"2405.05417","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/fishing-for-magikarp-automatically-detecting#ran","syntology_url":"https://syntology.ai/paper/2405.05417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05417"}},"official":{"repos":["cohere-ai/magikarp"],"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/knowledge-adaptation-from-large-language","slug":"knowledge-adaptation-from-large-language","title":"LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application","date":"2024-05-07","arxiv_id":"2405.03988","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/knowledge-adaptation-from-large-language#ran","syntology_url":"https://syntology.ai/paper/2405.03988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03988"}},"official":{"repos":["adxcreative/LEARN"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/seed-data-edit-technical-report-a-hybrid","slug":"seed-data-edit-technical-report-a-hybrid","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","date":"2024-05-07","arxiv_id":"2405.04007","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/seed-data-edit-technical-report-a-hybrid#ran","syntology_url":"https://syntology.ai/paper/2405.04007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04007"}},"official":{"repos":["ailab-cvc/seed-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cos-enhancing-personalization-and-mitigating","slug":"cos-enhancing-personalization-and-mitigating","title":"CoS: Enhancing Personalization and Mitigating Bias with Context Steering","date":"2024-05-02","arxiv_id":"2405.01768","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/cos-enhancing-personalization-and-mitigating#ran","syntology_url":"https://syntology.ai/paper/2405.01768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01768"}},"official":{"repos":["sashrikap/context-steering"],"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/distillation-matters-empowering-sequential","slug":"distillation-matters-empowering-sequential","title":"Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model","date":"2024-05-01","arxiv_id":"2405.00338","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/distillation-matters-empowering-sequential#ran","syntology_url":"https://syntology.ai/paper/2405.00338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00338"}},"official":{"repos":["istarryn/dllm2rec"],"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/biomedrag-a-retrieval-augmented-large","slug":"biomedrag-a-retrieval-augmented-large","title":"BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine","date":"2024-05-01","arxiv_id":"2405.00465","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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/biomedrag-a-retrieval-augmented-large#ran","syntology_url":"https://syntology.ai/paper/2405.00465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00465"}},"official":{"repos":["toneli/petailor-for-bio-triple-extraction"],"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/is-bigger-edit-batch-size-always-better-an","slug":"is-bigger-edit-batch-size-always-better-an","title":"Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3","date":"2024-05-01","arxiv_id":"2405.00664","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/is-bigger-edit-batch-size-always-better-an#ran","syntology_url":"https://syntology.ai/paper/2405.00664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00664"}},"official":{"repos":["scalable-model-editing/unified-model-editing"],"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/tablevqa-bench-a-visual-question-answering","slug":"tablevqa-bench-a-visual-question-answering","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","date":"2024-04-30","arxiv_id":"2404.19205","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/tablevqa-bench-a-visual-question-answering#ran","syntology_url":"https://syntology.ai/paper/2404.19205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19205"}},"official":{"repos":["naver-ai/tablevqabench"],"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/ranked-list-truncation-for-large-language","slug":"ranked-list-truncation-for-large-language","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","date":"2024-04-28","arxiv_id":"2404.18185","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ranked-list-truncation-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.18185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18185"}},"official":{"repos":["chuanmeng/rlt4reranking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/worldgpt-empowering-llm-as-multimodal-world","slug":"worldgpt-empowering-llm-as-multimodal-world","title":"WorldGPT: Empowering LLM as Multimodal World Model","date":"2024-04-28","arxiv_id":"2404.18202","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/worldgpt-empowering-llm-as-multimodal-world#ran","syntology_url":"https://syntology.ai/paper/2404.18202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18202"}},"official":{"repos":["dcdmllm/worldgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-head-mechanistically-explains-long","slug":"retrieval-head-mechanistically-explains-long","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","date":"2024-04-24","arxiv_id":"2404.15574","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieval-head-mechanistically-explains-long#ran","syntology_url":"https://syntology.ai/paper/2404.15574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15574"}},"official":{"repos":["nightdessert/retrieval_head"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/studying-large-language-model-behaviors-under","slug":"studying-large-language-model-behaviors-under","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","date":"2024-04-24","arxiv_id":"2404.16032","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":8,"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/studying-large-language-model-behaviors-under#ran","syntology_url":"https://syntology.ai/paper/2404.16032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16032"}},"official":{"repos":["kortukov/realistic_knowledge_conflicts"],"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/attacks-on-third-party-apis-of-large-language","slug":"attacks-on-third-party-apis-of-large-language","title":"Attacks on Third-Party APIs of Large Language Models","date":"2024-04-24","arxiv_id":"2404.16891","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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/attacks-on-third-party-apis-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.16891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16891"}},"official":{"repos":["vk0812/third-party-attacks-on-llms"],"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/boter-bootstrapping-knowledge-selection-and","slug":"boter-bootstrapping-knowledge-selection-and","title":"Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering","date":"2024-04-22","arxiv_id":"2404.13947","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/boter-bootstrapping-knowledge-selection-and#ran","syntology_url":"https://syntology.ai/paper/2404.13947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13947"}},"official":{"repos":["haodongze/self-ksel-qans"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cofinal-enhancing-action-quality-assessment","slug":"cofinal-enhancing-action-quality-assessment","title":"CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment","date":"2024-04-22","arxiv_id":"2404.13999","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cofinal-enhancing-action-quality-assessment#ran","syntology_url":"https://syntology.ai/paper/2404.13999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13999"}},"official":{"repos":["zhoukanglei/cofinal_aqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/how-good-are-low-bit-quantized-llama3-models","slug":"how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","date":"2024-04-22","arxiv_id":"2404.14047","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-good-are-low-bit-quantized-llama3-models#ran","syntology_url":"https://syntology.ai/paper/2404.14047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14047"}},"official":{"repos":["macaronlin/llama3-quantization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/melange-cost-efficient-large-language-model","slug":"melange-cost-efficient-large-language-model","title":"Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","date":"2024-04-22","arxiv_id":"2404.14527","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/melange-cost-efficient-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2404.14527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14527"}},"official":{"repos":["tyler-griggs/melange-release"],"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/evaluating-retrieval-quality-in-retrieval","slug":"evaluating-retrieval-quality-in-retrieval","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","date":"2024-04-21","arxiv_id":"2404.13781","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":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) · 0 unverified","sample_list":"/paper/evaluating-retrieval-quality-in-retrieval#ran","syntology_url":"https://syntology.ai/paper/2404.13781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13781"}},"official":{"repos":["alirezasalemi7/erag"],"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/finerec-exploring-fine-grained-sequential","slug":"finerec-exploring-fine-grained-sequential","title":"FineRec:Exploring Fine-grained Sequential Recommendation","date":"2024-04-19","arxiv_id":"2404.12975","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/finerec-exploring-fine-grained-sequential#ran","syntology_url":"https://syntology.ai/paper/2404.12975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12975"}},"official":{"repos":["zhang-xiaokun/finerec"],"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/groma-localized-visual-tokenization-for","slug":"groma-localized-visual-tokenization-for","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","date":"2024-04-19","arxiv_id":"2404.13013","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/groma-localized-visual-tokenization-for#ran","syntology_url":"https://syntology.ai/paper/2404.13013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13013"}},"official":{"repos":["FoundationVision/Groma"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mova-adapting-mixture-of-vision-experts-to","slug":"mova-adapting-mixture-of-vision-experts-to","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","date":"2024-04-19","arxiv_id":"2404.13046","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mova-adapting-mixture-of-vision-experts-to#ran","syntology_url":"https://syntology.ai/paper/2404.13046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13046"}},"official":{"repos":["templex98/mova"],"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","unlocated"]}}},{"url":"/paper/improving-composed-image-retrieval-via","slug":"improving-composed-image-retrieval-via","title":"Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives","date":"2024-04-17","arxiv_id":"2404.11317","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":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/improving-composed-image-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2404.11317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11317"}},"official":{"repos":["BUAADreamer/SPN4CIR"],"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/balancing-speciality-and-versatility-a-coarse","slug":"balancing-speciality-and-versatility-a-coarse","title":"Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model","date":"2024-04-16","arxiv_id":"2404.10306","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/balancing-speciality-and-versatility-a-coarse#ran","syntology_url":"https://syntology.ai/paper/2404.10306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10306"}},"official":{"repos":["rattlesnakey/cofitune"],"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/in2in-leveraging-individual-information-to-1","slug":"in2in-leveraging-individual-information-to-1","title":"in2IN: Leveraging individual Information to Generate Human INteractions","date":"2024-04-15","arxiv_id":"2404.09988","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/in2in-leveraging-individual-information-to-1#ran","syntology_url":"https://syntology.ai/paper/2404.09988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09988"}},"official":{"repos":["pabloruizponce/in2IN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ming-moe-enhancing-medical-multi-task","slug":"ming-moe-enhancing-medical-multi-task","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","date":"2024-04-13","arxiv_id":"2404.09027","repositories_listed":2,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 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; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ming-moe-enhancing-medical-multi-task#ran","syntology_url":"https://syntology.ai/paper/2404.09027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09027"}},"official":{"repos":["mediabrain-sjtu/ming"],"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":["listed","official"]}}},{"url":"/paper/scalable-language-model-with-generalized","slug":"scalable-language-model-with-generalized","title":"Scalable Language Model with Generalized Continual Learning","date":"2024-04-11","arxiv_id":"2404.07470","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"8 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scalable-language-model-with-generalized#ran","syntology_url":"https://syntology.ai/paper/2404.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07470"}},"official":{"repos":["pbihao/slm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/from-words-to-numbers-your-large-language","slug":"from-words-to-numbers-your-large-language","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","date":"2024-04-11","arxiv_id":"2404.07544","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-words-to-numbers-your-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.07544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07544"}},"official":{"repos":["robertvacareanu/llm4regression"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ferret-v2-an-improved-baseline-for-referring","slug":"ferret-v2-an-improved-baseline-for-referring","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","date":"2024-04-11","arxiv_id":"2404.07973","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":5,"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/ferret-v2-an-improved-baseline-for-referring#ran","syntology_url":"https://syntology.ai/paper/2404.07973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07973"}},"official":null}}],"record_sha256":"10ecbc02afa89035521f6e11459b05bee04fbd61c44cb302e27daf40576fbfcb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}