{"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/2","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":2,"pages_in_order":9,"rows_per_page":100,"rows":[101,200],"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/1","next":"/task/large-language-model/papers/ran/3","papers":[{"url":"/paper/enhancing-reasoning-to-adapt-large-language","slug":"enhancing-reasoning-to-adapt-large-language","title":"Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications","date":"2025-02-05","arxiv_id":"2502.04384","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/enhancing-reasoning-to-adapt-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.04384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04384"}},"official":{"repos":["wenboown/generative-ai-for-semiconductor-physical-design"],"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/citer-collaborative-inference-for-efficient","slug":"citer-collaborative-inference-for-efficient","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","date":"2025-02-04","arxiv_id":"2502.01976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/citer-collaborative-inference-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2502.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01976"}},"official":{"repos":["aiming-lab/CITER"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-generate-unit-tests-for-automated","slug":"learning-to-generate-unit-tests-for-automated","title":"Learning to Generate Unit Tests for Automated Debugging","date":"2025-02-03","arxiv_id":"2502.01619","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-generate-unit-tests-for-automated#ran","syntology_url":"https://syntology.ai/paper/2502.01619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01619"}},"official":{"repos":["archiki/utgendebug"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-safety-alignment-is-divergence-estimation","slug":"llm-safety-alignment-is-divergence-estimation","title":"LLM Safety Alignment is Divergence Estimation in Disguise","date":"2025-02-02","arxiv_id":"2502.00657","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"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) · 8 unverified","sample_list":"/paper/llm-safety-alignment-is-divergence-estimation#ran","syntology_url":"https://syntology.ai/paper/2502.00657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00657"}},"official":{"repos":["rhaldarpurdue/kldo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-centric-token-compression-in-large","slug":"vision-centric-token-compression-in-large","title":"Vision-centric Token Compression in Large Language Model","date":"2025-02-02","arxiv_id":"2502.00791","repositories_listed":0,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"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) · 7 unverified","sample_list":"/paper/vision-centric-token-compression-in-large#ran","syntology_url":"https://syntology.ai/paper/2502.00791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00791"}},"official":null}},{"url":"/paper/llmdet-learning-strong-open-vocabulary-object","slug":"llmdet-learning-strong-open-vocabulary-object","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","date":"2025-01-31","arxiv_id":"2501.18954","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"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) · 1 unverified","sample_list":"/paper/llmdet-learning-strong-open-vocabulary-object#ran","syntology_url":"https://syntology.ai/paper/2501.18954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18954"}},"official":{"repos":["isee-laboratory/llmdet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/differentially-private-steering-for-large","slug":"differentially-private-steering-for-large","title":"Differentially Private Steering for Large Language Model Alignment","date":"2025-01-30","arxiv_id":"2501.18532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differentially-private-steering-for-large#ran","syntology_url":"https://syntology.ai/paper/2501.18532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18532"}},"official":{"repos":["ukplab/iclr2025-psa"],"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/vlmaterial-procedural-material-generation","slug":"vlmaterial-procedural-material-generation","title":"VLMaterial: Procedural Material Generation with Large Vision-Language Models","date":"2025-01-27","arxiv_id":"2501.18623","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/vlmaterial-procedural-material-generation#ran","syntology_url":"https://syntology.ai/paper/2501.18623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18623"}},"official":null}},{"url":"/paper/hermes-a-unified-self-driving-world-model-for","slug":"hermes-a-unified-self-driving-world-model-for","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","date":"2025-01-24","arxiv_id":"2501.14729","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/hermes-a-unified-self-driving-world-model-for#ran","syntology_url":"https://syntology.ai/paper/2501.14729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.14729"}},"official":{"repos":["lmd0311/hermes"],"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/ostquant-refining-large-language-model","slug":"ostquant-refining-large-language-model","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","date":"2025-01-23","arxiv_id":"2501.13987","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/ostquant-refining-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2501.13987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13987"}},"official":{"repos":["brotherhappy/ostquant"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/endochat-grounded-multimodal-large-language","slug":"endochat-grounded-multimodal-large-language","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","date":"2025-01-20","arxiv_id":"2501.11347","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/endochat-grounded-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2501.11347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11347"}},"official":{"repos":["gkw0010/endochat"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pike-rag-specialized-knowledge-and-rationale","slug":"pike-rag-specialized-knowledge-and-rationale","title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","date":"2025-01-20","arxiv_id":"2501.11551","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pike-rag-specialized-knowledge-and-rationale#ran","syntology_url":"https://syntology.ai/paper/2501.11551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11551"}},"official":{"repos":["microsoft/pike-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zep-a-temporal-knowledge-graph-architecture","slug":"zep-a-temporal-knowledge-graph-architecture","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","date":"2025-01-20","arxiv_id":"2501.13956","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/zep-a-temporal-knowledge-graph-architecture#ran","syntology_url":"https://syntology.ai/paper/2501.13956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13956"}},"official":{"repos":["getzep/graphiti"],"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/beyond-reward-hacking-causal-rewards-for","slug":"beyond-reward-hacking-causal-rewards-for","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","date":"2025-01-16","arxiv_id":"2501.09620","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":0,"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/beyond-reward-hacking-causal-rewards-for#ran","syntology_url":"https://syntology.ai/paper/2501.09620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.09620"}},"official":{"repos":["tatsu-lab/alpaca_farm"],"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/monte-carlo-tree-search-for-comprehensive","slug":"monte-carlo-tree-search-for-comprehensive","title":"Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design","date":"2025-01-15","arxiv_id":"2501.08603","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":1,"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/monte-carlo-tree-search-for-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2501.08603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08603"}},"official":{"repos":["zz1358m/mcts-ahd-master"],"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/llava-st-a-multimodal-large-language-model","slug":"llava-st-a-multimodal-large-language-model","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","date":"2025-01-14","arxiv_id":"2501.08282","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 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) · 4 unverified","sample_list":"/paper/llava-st-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2501.08282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08282"}},"official":{"repos":["appletea233/llava-st"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-image-generation-fidelity-via","slug":"enhancing-image-generation-fidelity-via","title":"Enhancing Image Generation Fidelity via Progressive Prompts","date":"2025-01-13","arxiv_id":"2501.07070","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/enhancing-image-generation-fidelity-via#ran","syntology_url":"https://syntology.ai/paper/2501.07070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07070"}},"official":{"repos":["zhenxiong-dl/icassp2025-rcac"],"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/ladder-residual-parallelism-aware","slug":"ladder-residual-parallelism-aware","title":"Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping","date":"2025-01-11","arxiv_id":"2501.06589","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ladder-residual-parallelism-aware#ran","syntology_url":"https://syntology.ai/paper/2501.06589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06589"}},"official":{"repos":["mayank31398/ladder-residual-inference"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/valley2-exploring-multimodal-models-with","slug":"valley2-exploring-multimodal-models-with","title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","date":"2025-01-10","arxiv_id":"2501.05901","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":1,"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/valley2-exploring-multimodal-models-with#ran","syntology_url":"https://syntology.ai/paper/2501.05901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05901"}},"official":{"repos":["bytedance/valley"],"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/establishing-baselines-for-generative","slug":"establishing-baselines-for-generative","title":"Establishing baselines for generative discovery of inorganic crystals","date":"2025-01-04","arxiv_id":"2501.02144","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/establishing-baselines-for-generative#ran","syntology_url":"https://syntology.ai/paper/2501.02144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02144"}},"official":{"repos":["bartel-group/matgen_baselines"],"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/an-engorgio-prompt-makes-large-language-model","slug":"an-engorgio-prompt-makes-large-language-model","title":"An Engorgio Prompt Makes Large Language Model Babble on","date":"2024-12-27","arxiv_id":"2412.19394","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-engorgio-prompt-makes-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.19394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19394"}},"official":{"repos":["jianshuod/engorgio-prompt"],"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/alignment-faking-in-large-language-models","slug":"alignment-faking-in-large-language-models","title":"Alignment faking in large language models","date":"2024-12-18","arxiv_id":"2412.14093","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/alignment-faking-in-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2412.14093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14093"}},"official":{"repos":["redwoodresearch/alignment_faking_public"],"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/preference-oriented-supervised-fine-tuning","slug":"preference-oriented-supervised-fine-tuning","title":"Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models","date":"2024-12-17","arxiv_id":"2412.12865","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/preference-oriented-supervised-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2412.12865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12865"}},"official":{"repos":["Savannah120/alignment-handbook-PoFT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chattime-a-unified-multimodal-time-series","slug":"chattime-a-unified-multimodal-time-series","title":"ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data","date":"2024-12-16","arxiv_id":"2412.11376","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/chattime-a-unified-multimodal-time-series#ran","syntology_url":"https://syntology.ai/paper/2412.11376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11376"}},"official":{"repos":["forestsking/chattime"],"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/llms-can-simulate-standardized-patients-via","slug":"llms-can-simulate-standardized-patients-via","title":"LLMs Can Simulate Standardized Patients via Agent Coevolution","date":"2024-12-16","arxiv_id":"2412.11716","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/llms-can-simulate-standardized-patients-via#ran","syntology_url":"https://syntology.ai/paper/2412.11716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11716"}},"official":{"repos":["zjumai/evopatient"],"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/you-name-it-i-run-it-an-llm-agent-to-execute","slug":"you-name-it-i-run-it-an-llm-agent-to-execute","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","date":"2024-12-13","arxiv_id":"2412.10133","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/you-name-it-i-run-it-an-llm-agent-to-execute#ran","syntology_url":"https://syntology.ai/paper/2412.10133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10133"}},"official":{"repos":["sola-st/executionagent"],"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/from-allies-to-adversaries-manipulating-llm","slug":"from-allies-to-adversaries-manipulating-llm","title":"From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection","date":"2024-12-13","arxiv_id":"2412.10198","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":2,"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/from-allies-to-adversaries-manipulating-llm#ran","syntology_url":"https://syntology.ai/paper/2412.10198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10198"}},"official":{"repos":["anonymous-lgtm/toolcommander"],"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/sprec-leveraging-self-play-to-debias","slug":"sprec-leveraging-self-play-to-debias","title":"SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations","date":"2024-12-12","arxiv_id":"2412.09243","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sprec-leveraging-self-play-to-debias#ran","syntology_url":"https://syntology.ai/paper/2412.09243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09243"}},"official":{"repos":["regionch/sprec"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-multimodal-large-language-model","slug":"towards-a-multimodal-large-language-model","title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine","date":"2024-12-12","arxiv_id":"2412.09278","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.09278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09278"}},"official":{"repos":["shawnhuang497/medplib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/atprompt-textual-prompt-learning-with","slug":"atprompt-textual-prompt-learning-with","title":"ATPrompt: Textual Prompt Learning with Embedded Attributes","date":"2024-12-12","arxiv_id":"2412.09442","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/atprompt-textual-prompt-learning-with#ran","syntology_url":"https://syntology.ai/paper/2412.09442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09442"}},"official":null}},{"url":"/paper/concept-bottleneck-large-language-models","slug":"concept-bottleneck-large-language-models","title":"Concept Bottleneck Large Language Models","date":"2024-12-11","arxiv_id":"2412.07992","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/concept-bottleneck-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2412.07992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07992"}},"official":{"repos":["trustworthy-ml-lab/cb-llms"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pyod-2-a-python-library-for-outlier-detection","slug":"pyod-2-a-python-library-for-outlier-detection","title":"PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selection","date":"2024-12-11","arxiv_id":"2412.12154","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pyod-2-a-python-library-for-outlier-detection#ran","syntology_url":"https://syntology.ai/paper/2412.12154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12154"}},"official":{"repos":["yzhao062/pyod"],"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/granite-guardian","slug":"granite-guardian","title":"Granite Guardian","date":"2024-12-10","arxiv_id":"2412.07724","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/granite-guardian#ran","syntology_url":"https://syntology.ai/paper/2412.07724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07724"}},"official":{"repos":["ibm-granite/granite-guardian"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-optimization-of-antibodies-informed","slug":"bayesian-optimization-of-antibodies-informed","title":"Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences","date":"2024-12-10","arxiv_id":"2412.07763","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bayesian-optimization-of-antibodies-informed#ran","syntology_url":"https://syntology.ai/paper/2412.07763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07763"}},"official":{"repos":["alannawzadamin/clonebo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/linvt-empower-your-image-level-large-language","slug":"linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","arxiv_id":"2412.05185","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":1,"n_no_contract":6,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/linvt-empower-your-image-level-large-language#ran","syntology_url":"https://syntology.ai/paper/2412.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05185"}},"official":{"repos":["gls0425/linvt"],"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","unlocated"]}}},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/liquid-language-models-are-scalable-multi","slug":"liquid-language-models-are-scalable-multi","title":"Liquid: Language Models are Scalable Multi-modal Generators","date":"2024-12-05","arxiv_id":"2412.04332","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/liquid-language-models-are-scalable-multi#ran","syntology_url":"https://syntology.ai/paper/2412.04332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04332"}},"official":{"repos":["foundationvision/liquid"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/rilq-rank-insensitive-lora-based-quantization","slug":"rilq-rank-insensitive-lora-based-quantization","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","date":"2024-12-02","arxiv_id":"2412.01129","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rilq-rank-insensitive-lora-based-quantization#ran","syntology_url":"https://syntology.ai/paper/2412.01129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01129"}},"official":{"repos":["aiha-lab/rilq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/data-centric-and-heterogeneity-adaptive","slug":"data-centric-and-heterogeneity-adaptive","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","date":"2024-12-02","arxiv_id":"2412.01523","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/data-centric-and-heterogeneity-adaptive#ran","syntology_url":"https://syntology.ai/paper/2412.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01523"}},"official":null}},{"url":"/paper/pushing-the-limits-of-large-language-model","slug":"pushing-the-limits-of-large-language-model","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","date":"2024-11-26","arxiv_id":"2411.17525","repositories_listed":2,"syntology":{"n":36,"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":15,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/pushing-the-limits-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.17525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17525"}},"official":null}},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-agentic-schema-refinement","slug":"towards-agentic-schema-refinement","title":"Towards Agentic Schema Refinement","date":"2024-11-25","arxiv_id":"2412.07786","repositories_listed":0,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"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) · 4 unverified","sample_list":"/paper/towards-agentic-schema-refinement#ran","syntology_url":"https://syntology.ai/paper/2412.07786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07786"}},"official":null}},{"url":"/paper/scribeagent-towards-specialized-web-agents","slug":"scribeagent-towards-specialized-web-agents","title":"ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data","date":"2024-11-22","arxiv_id":"2411.15004","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/scribeagent-towards-specialized-web-agents#ran","syntology_url":"https://syntology.ai/paper/2411.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15004"}},"official":{"repos":["colonylabs/ScribeAgent"],"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/piors-personalized-intelligent-outpatient","slug":"piors-personalized-intelligent-outpatient","title":"PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation","date":"2024-11-21","arxiv_id":"2411.13902","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":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) · 4 unverified","sample_list":"/paper/piors-personalized-intelligent-outpatient#ran","syntology_url":"https://syntology.ai/paper/2411.13902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13902"}},"official":{"repos":["fudandisc/piors"],"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/drpruning-efficient-large-language-model","slug":"drpruning-efficient-large-language-model","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","date":"2024-11-21","arxiv_id":"2411.14055","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/drpruning-efficient-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.14055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14055"}},"official":{"repos":["hexuandeng/drpruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/planning-driven-programming-a-large-language","slug":"planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","arxiv_id":"2411.14503","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/planning-driven-programming-a-large-language#ran","syntology_url":"https://syntology.ai/paper/2411.14503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14503"}},"official":{"repos":["you68681/lpw"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/oasis-open-agents-social-interaction","slug":"oasis-open-agents-social-interaction","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","date":"2024-11-18","arxiv_id":"2411.11581","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/oasis-open-agents-social-interaction#ran","syntology_url":"https://syntology.ai/paper/2411.11581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11581"}},"official":{"repos":["camel-ai/oasis"],"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/does-unlearning-truly-unlearn-a-black-box","slug":"does-unlearning-truly-unlearn-a-black-box","title":"Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods","date":"2024-11-18","arxiv_id":"2411.12103","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/does-unlearning-truly-unlearn-a-black-box#ran","syntology_url":"https://syntology.ai/paper/2411.12103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12103"}},"official":{"repos":["jaidoshi/knowledge-erasure"],"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/multi-stage-vision-token-dropping-towards","slug":"multi-stage-vision-token-dropping-towards","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","date":"2024-11-16","arxiv_id":"2411.10803","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-stage-vision-token-dropping-towards#ran","syntology_url":"https://syntology.ai/paper/2411.10803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10803"}},"official":{"repos":["liuting20/mustdrop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lhrs-bot-nova-improved-multimodal-large","slug":"lhrs-bot-nova-improved-multimodal-large","title":"LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation","date":"2024-11-14","arxiv_id":"2411.09301","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lhrs-bot-nova-improved-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2411.09301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09301"}},"official":{"repos":["NJU-LHRS/LHRS-Bot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/squeezed-attention-accelerating-long-context","slug":"squeezed-attention-accelerating-long-context","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","date":"2024-11-14","arxiv_id":"2411.09688","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":15,"phrase":"12 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/squeezed-attention-accelerating-long-context#ran","syntology_url":"https://syntology.ai/paper/2411.09688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09688"}},"official":{"repos":["SqueezeAILab/SqueezedAttention"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/magicquill-an-intelligent-interactive-image","slug":"magicquill-an-intelligent-interactive-image","title":"MagicQuill: An Intelligent Interactive Image Editing System","date":"2024-11-14","arxiv_id":"2411.09703","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":12,"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) · 0 unverified","sample_list":"/paper/magicquill-an-intelligent-interactive-image#ran","syntology_url":"https://syntology.ai/paper/2411.09703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09703"}},"official":{"repos":["ant-research/MagicQuill"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-neo-parameter-efficient-knowledge","slug":"llm-neo-parameter-efficient-knowledge","title":"LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models","date":"2024-11-11","arxiv_id":"2411.06839","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"12 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-neo-parameter-efficient-knowledge#ran","syntology_url":"https://syntology.ai/paper/2411.06839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06839"}},"official":null}},{"url":"/paper/the-super-weight-in-large-language-models","slug":"the-super-weight-in-large-language-models","title":"The Super Weight in Large Language Models","date":"2024-11-11","arxiv_id":"2411.07191","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/the-super-weight-in-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2411.07191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07191"}},"official":{"repos":["mengxiayu/llmsuperweight"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/suffixdecoding-a-model-free-approach-to","slug":"suffixdecoding-a-model-free-approach-to","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","date":"2024-11-07","arxiv_id":"2411.04975","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/suffixdecoding-a-model-free-approach-to#ran","syntology_url":"https://syntology.ai/paper/2411.04975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04975"}},"official":{"repos":["snowflakedb/arcticinference"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-bradley-terry-models-in-preference","slug":"rethinking-bradley-terry-models-in-preference","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","date":"2024-11-07","arxiv_id":"2411.04991","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-bradley-terry-models-in-preference#ran","syntology_url":"https://syntology.ai/paper/2411.04991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04991"}},"official":{"repos":["holarissun/rewardmodelingbeyondbradleyterry"],"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/v-dpo-mitigating-hallucination-in-large","slug":"v-dpo-mitigating-hallucination-in-large","title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization","date":"2024-11-05","arxiv_id":"2411.02712","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/v-dpo-mitigating-hallucination-in-large#ran","syntology_url":"https://syntology.ai/paper/2411.02712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02712"}},"official":{"repos":["yuxixie/v-dpo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-expert-prompting-improves-reliability","slug":"multi-expert-prompting-improves-reliability","title":"Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models","date":"2024-11-01","arxiv_id":"2411.00492","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/multi-expert-prompting-improves-reliability#ran","syntology_url":"https://syntology.ai/paper/2411.00492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00492"}},"official":{"repos":["dxlong2000/multi-expert-prompting"],"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/plan-on-graph-self-correcting-adaptive","slug":"plan-on-graph-self-correcting-adaptive","title":"Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs","date":"2024-10-31","arxiv_id":"2410.23875","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"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) · 5 unverified","sample_list":"/paper/plan-on-graph-self-correcting-adaptive#ran","syntology_url":"https://syntology.ai/paper/2410.23875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23875"}},"official":{"repos":["liyichen-cly/pog"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ez-hoi-vlm-adaptation-via-guided-prompt","slug":"ez-hoi-vlm-adaptation-via-guided-prompt","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","date":"2024-10-31","arxiv_id":"2410.23904","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ez-hoi-vlm-adaptation-via-guided-prompt#ran","syntology_url":"https://syntology.ai/paper/2410.23904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23904"}},"official":{"repos":["chelsielei/ez-hoi"],"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/matchmaker-self-improving-large-language","slug":"matchmaker-self-improving-large-language","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","date":"2024-10-31","arxiv_id":"2410.24105","repositories_listed":0,"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/matchmaker-self-improving-large-language#ran","syntology_url":"https://syntology.ai/paper/2410.24105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24105"}},"official":null}},{"url":"/paper/llamo-large-language-model-based-molecular","slug":"llamo-large-language-model-based-molecular","title":"LLaMo: Large Language Model-based Molecular Graph Assistant","date":"2024-10-31","arxiv_id":"2411.00871","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"10 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llamo-large-language-model-based-molecular#ran","syntology_url":"https://syntology.ai/paper/2411.00871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00871"}},"official":{"repos":["mlvlab/llamo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/online-intrinsic-rewards-for-decision-making","slug":"online-intrinsic-rewards-for-decision-making","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","date":"2024-10-30","arxiv_id":"2410.23022","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"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) · 3 unverified","sample_list":"/paper/online-intrinsic-rewards-for-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.23022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23022"}},"official":{"repos":["facebookresearch/oni"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/toward-understanding-in-context-vs-in-weight","slug":"toward-understanding-in-context-vs-in-weight","title":"Toward Understanding In-context vs. In-weight Learning","date":"2024-10-30","arxiv_id":"2410.23042","repositories_listed":0,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/toward-understanding-in-context-vs-in-weight#ran","syntology_url":"https://syntology.ai/paper/2410.23042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23042"}},"official":null}},{"url":"/paper/real-time-personalization-for-llm-based","slug":"real-time-personalization-for-llm-based","title":"Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning","date":"2024-10-30","arxiv_id":"2410.23136","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":1,"n_no_contract":5,"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, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-personalization-for-llm-based#ran","syntology_url":"https://syntology.ai/paper/2410.23136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23136"}},"official":{"repos":["ym689/rec_icl"],"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/sg-bench-evaluating-llm-safety-generalization","slug":"sg-bench-evaluating-llm-safety-generalization","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","date":"2024-10-29","arxiv_id":"2410.21965","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/sg-bench-evaluating-llm-safety-generalization#ran","syntology_url":"https://syntology.ai/paper/2410.21965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21965"}},"official":{"repos":["MurrayTom/SG-Bench"],"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/protecting-privacy-in-multimodal-large","slug":"protecting-privacy-in-multimodal-large","title":"Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench","date":"2024-10-29","arxiv_id":"2410.22108","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/protecting-privacy-in-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2410.22108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22108"}},"official":{"repos":["franciscoliu/MLLMU-Bench"],"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/rare-to-frequent-unlocking-compositional","slug":"rare-to-frequent-unlocking-compositional","title":"Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance","date":"2024-10-29","arxiv_id":"2410.22376","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rare-to-frequent-unlocking-compositional#ran","syntology_url":"https://syntology.ai/paper/2410.22376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22376"}},"official":{"repos":["krafton-ai/rare-to-frequent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/llmcbench-benchmarking-large-language-model","slug":"llmcbench-benchmarking-large-language-model","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","date":"2024-10-28","arxiv_id":"2410.21352","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llmcbench-benchmarking-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.21352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21352"}},"official":{"repos":["aboveparadise/llmcbench"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/trajagent-an-agent-framework-for-unified","slug":"trajagent-an-agent-framework-for-unified","title":"TrajAgent: An Agent Framework for Unified Trajectory Modelling","date":"2024-10-27","arxiv_id":"2410.20445","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/trajagent-an-agent-framework-for-unified#ran","syntology_url":"https://syntology.ai/paper/2410.20445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20445"}},"official":{"repos":["tsinghua-fib-lab/trajagent"],"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/implementation-and-application-of-an","slug":"implementation-and-application-of-an","title":"Implementation and Application of an Intelligibility Protocol for Interaction with an LLM","date":"2024-10-27","arxiv_id":"2410.20600","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/implementation-and-application-of-an#ran","syntology_url":"https://syntology.ai/paper/2410.20600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20600"}},"official":{"repos":["karannb/interact"],"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/swe-search-enhancing-software-agents-with","slug":"swe-search-enhancing-software-agents-with","title":"SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement","date":"2024-10-26","arxiv_id":"2410.20285","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/swe-search-enhancing-software-agents-with#ran","syntology_url":"https://syntology.ai/paper/2410.20285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20285"}},"official":{"repos":["aorwall/moatless-tools","aorwall/moatless-tree-search"],"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/coat-compressing-optimizer-states-and","slug":"coat-compressing-optimizer-states-and","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","date":"2024-10-25","arxiv_id":"2410.19313","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coat-compressing-optimizer-states-and#ran","syntology_url":"https://syntology.ai/paper/2410.19313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19313"}},"official":{"repos":["nvlabs/coat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/navigating-noisy-feedback-enhancing","slug":"navigating-noisy-feedback-enhancing","title":"Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models","date":"2024-10-22","arxiv_id":"2410.17389","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navigating-noisy-feedback-enhancing#ran","syntology_url":"https://syntology.ai/paper/2410.17389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17389"}},"official":{"repos":["sy-shi/RLAIF_ScoreDiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/residual-vector-quantization-for-kv-cache","slug":"residual-vector-quantization-for-kv-cache","title":"Residual vector quantization for KV cache compression in large language model","date":"2024-10-21","arxiv_id":"2410.15704","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/residual-vector-quantization-for-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2410.15704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15704"}},"official":{"repos":["iankur/vqllm"],"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/spa-bench-a-comprehensive-benchmark-for","slug":"spa-bench-a-comprehensive-benchmark-for","title":"SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation","date":"2024-10-19","arxiv_id":"2410.15164","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spa-bench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2410.15164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15164"}},"official":{"repos":["ai-agents-2030/SPA-Bench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}},{"url":"/paper/sprig-improving-large-language-model","slug":"sprig-improving-large-language-model","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","date":"2024-10-18","arxiv_id":"2410.14826","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sprig-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.14826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14826"}},"official":{"repos":["orange0629/prompting"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/aixcoder-7b-a-lightweight-and-effective-large","slug":"aixcoder-7b-a-lightweight-and-effective-large","title":"aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing","date":"2024-10-17","arxiv_id":"2410.13187","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aixcoder-7b-a-lightweight-and-effective-large#ran","syntology_url":"https://syntology.ai/paper/2410.13187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13187"}},"official":{"repos":["aixcoder-plugin/aixcoder-7b"],"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/on-the-role-of-attention-heads-in-large","slug":"on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","arxiv_id":"2410.13708","repositories_listed":1,"syntology":{"n":24,"n_ran":16,"n_constructed":0,"n_ran_checked":8,"n_instrument":8,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/on-the-role-of-attention-heads-in-large#ran","syntology_url":"https://syntology.ai/paper/2410.13708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13708"}},"official":{"repos":["ydyjya/safetyheadattribution"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/fire-fact-checking-with-iterative-retrieval","slug":"fire-fact-checking-with-iterative-retrieval","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","date":"2024-10-17","arxiv_id":"2411.00784","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fire-fact-checking-with-iterative-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.00784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00784"}},"official":{"repos":["mbzuai-nlp/fire"],"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/how-to-leverage-demonstration-data-in","slug":"how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","arxiv_id":"2410.10093","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/how-to-leverage-demonstration-data-in#ran","syntology_url":"https://syntology.ai/paper/2410.10093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10093"}},"official":{"repos":["tengxiao1/gsil"],"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/longmemeval-benchmarking-chat-assistants-on","slug":"longmemeval-benchmarking-chat-assistants-on","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","date":"2024-10-14","arxiv_id":"2410.10813","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/longmemeval-benchmarking-chat-assistants-on#ran","syntology_url":"https://syntology.ai/paper/2410.10813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10813"}},"official":{"repos":["xiaowu0162/longmemeval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/retraining-free-merging-of-sparse-mixture-of","slug":"retraining-free-merging-of-sparse-mixture-of","title":"Retraining-Free Merging of Sparse MoE via Hierarchical Clustering","date":"2024-10-11","arxiv_id":"2410.08589","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"15 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; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/retraining-free-merging-of-sparse-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.08589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08589"}},"official":{"repos":["wazenmai/hc-smoe"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/poisonbench-assessing-large-language-model","slug":"poisonbench-assessing-large-language-model","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","date":"2024-10-11","arxiv_id":"2410.08811","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/poisonbench-assessing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.08811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08811"}},"official":{"repos":["tingchenfu/poisonbench"],"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/onenet-a-fine-tuning-free-framework-for-few","slug":"onenet-a-fine-tuning-free-framework-for-few","title":"OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting","date":"2024-10-10","arxiv_id":"2410.07549","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/onenet-a-fine-tuning-free-framework-for-few#ran","syntology_url":"https://syntology.ai/paper/2410.07549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07549"}},"official":{"repos":["laquabe/OneNet"],"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/divide-and-translate-compositional-first","slug":"divide-and-translate-compositional-first","title":"Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning","date":"2024-10-10","arxiv_id":"2410.08047","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/divide-and-translate-compositional-first#ran","syntology_url":"https://syntology.ai/paper/2410.08047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08047"}},"official":{"repos":["Hyun-Ryu/clover"],"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/simplicity-prevails-rethinking-negative","slug":"simplicity-prevails-rethinking-negative","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","date":"2024-10-09","arxiv_id":"2410.07163","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/simplicity-prevails-rethinking-negative#ran","syntology_url":"https://syntology.ai/paper/2410.07163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07163"}},"official":{"repos":["OPTML-Group/Unlearn-Simple"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-modality-prior-induced","slug":"mitigating-modality-prior-induced","title":"Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality","date":"2024-10-07","arxiv_id":"2410.04780","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/mitigating-modality-prior-induced#ran","syntology_url":"https://syntology.ai/paper/2410.04780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04780"}},"official":{"repos":["the-martyr/causalmm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-inference-for-large-language-model","slug":"efficient-inference-for-large-language-model","title":"Efficient Inference for Large Language Model-based Generative Recommendation","date":"2024-10-07","arxiv_id":"2410.05165","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":1,"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 1 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/efficient-inference-for-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.05165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05165"}},"official":{"repos":["linxyhaha/atspeed"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/data-advisor-dynamic-data-curation-for-safety","slug":"data-advisor-dynamic-data-curation-for-safety","title":"Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models","date":"2024-10-07","arxiv_id":"2410.05269","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/data-advisor-dynamic-data-curation-for-safety#ran","syntology_url":"https://syntology.ai/paper/2410.05269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05269"}},"official":{"repos":["feiwang96/Data-Advisor"],"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/gensim-a-general-social-simulation-platform","slug":"gensim-a-general-social-simulation-platform","title":"GenSim: A General Social Simulation Platform with Large Language Model based Agents","date":"2024-10-06","arxiv_id":"2410.04360","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/gensim-a-general-social-simulation-platform#ran","syntology_url":"https://syntology.ai/paper/2410.04360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04360"}},"official":{"repos":["TangJiakai/GenSim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/enriching-music-descriptions-with-a-finetuned","slug":"enriching-music-descriptions-with-a-finetuned","title":"Enriching Music Descriptions with a Finetuned-LLM and Metadata for Text-to-Music Retrieval","date":"2024-10-04","arxiv_id":"2410.03264","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":1,"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/enriching-music-descriptions-with-a-finetuned#ran","syntology_url":"https://syntology.ai/paper/2410.03264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03264"}},"official":{"repos":["seungheondoh/music-text-representation-pp"],"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/one2set-large-language-model-best-partners","slug":"one2set-large-language-model-best-partners","title":"One2set + Large Language Model: Best Partners for Keyphrase Generation","date":"2024-10-04","arxiv_id":"2410.03421","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/one2set-large-language-model-best-partners#ran","syntology_url":"https://syntology.ai/paper/2410.03421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03421"}},"official":{"repos":["deeplearnxmu/kpg-setllm"],"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/you-know-what-i-m-saying-jailbreak-attack-via","slug":"you-know-what-i-m-saying-jailbreak-attack-via","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","date":"2024-10-04","arxiv_id":"2410.03857","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/you-know-what-i-m-saying-jailbreak-attack-via#ran","syntology_url":"https://syntology.ai/paper/2410.03857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03857"}},"official":{"repos":["lucas-ty/llm_implicit_reference"],"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/choices-are-more-important-than-efforts-llm","slug":"choices-are-more-important-than-efforts-llm","title":"Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration","date":"2024-10-03","arxiv_id":"2410.02511","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/choices-are-more-important-than-efforts-llm#ran","syntology_url":"https://syntology.ai/paper/2410.02511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02511"}},"official":{"repos":["hijkzzz/pymarl2"],"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/openmathinstruct-2-accelerating-ai-for-math","slug":"openmathinstruct-2-accelerating-ai-for-math","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","date":"2024-10-02","arxiv_id":"2410.01560","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}},"official":null}},{"url":"/paper/layerkv-optimizing-large-language-model","slug":"layerkv-optimizing-large-language-model","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","date":"2024-10-01","arxiv_id":"2410.00428","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/layerkv-optimizing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.00428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00428"}},"official":null}},{"url":"/paper/openkd-opening-prompt-diversity-for-zero-and","slug":"openkd-opening-prompt-diversity-for-zero-and","title":"OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection","date":"2024-09-30","arxiv_id":"2409.19899","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":14,"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/openkd-opening-prompt-diversity-for-zero-and#ran","syntology_url":"https://syntology.ai/paper/2409.19899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19899"}},"official":{"repos":["alanlusun/openkd"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-empowered-embedding","slug":"large-language-model-empowered-embedding","title":"LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation","date":"2024-09-30","arxiv_id":"2409.19925","repositories_listed":2,"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/large-language-model-empowered-embedding#ran","syntology_url":"https://syntology.ai/paper/2409.19925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19925"}},"official":{"repos":["applied-machine-learning-lab/llmemb","liuqidong07/LLMEmb"],"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"]}}}],"record_sha256":"e489cbe49212246c4b02188d4058578459c77567e22d83fc554ee168141985b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}