{"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":"/method/focus/papers/ran/4","list_of":"/method/focus","method":"Focus","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":4,"pages_in_order":15,"rows_per_page":100,"rows":[301,400],"of":1419,"counts":{"archive_papers_tagged":15340,"with_a_code_link":5193,"where_syntology_ran_a_sample":1419,"not_listed_spam_title":0,"listed":15340,"listed_where_code_ran":1419,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1210,"every_run_a_failure_of_syntologys_instrument":209,"listed_with_a_run_with_no_instrument_failure":1210,"listed_every_run_a_failure_of_syntologys_instrument":209,"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":"/method/focus/papers/ran/1","prev":"/method/focus/papers/ran/3","next":"/method/focus/papers/ran/5","papers":[{"paper":"/paper/odrl-a-benchmark-for-off-dynamics","slug":"odrl-a-benchmark-for-off-dynamics","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","date":"2024-10-28","arxiv_id":"2410.20750","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":3,"n_instrument":3,"unverified":2,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["offdynamicsrl/off-dynamics-rl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/recflow-an-industrial-full-flow","slug":"recflow-an-industrial-full-flow","title":"RecFlow: An Industrial Full Flow Recommendation Dataset","date":"2024-10-28","arxiv_id":"2410.20868","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["recflow-iclr/recflow"],"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"]}}},{"paper":"/paper/protscape-mapping-the-landscape-of-protein","slug":"protscape-mapping-the-landscape-of-protein","title":"ProtSCAPE: Mapping the landscape of protein conformations in molecular dynamics","date":"2024-10-27","arxiv_id":"2410.20317","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["KrishnaswamyLab/ProtSCAPE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-cosmic-scale-benchmark-for-symmetry","slug":"a-cosmic-scale-benchmark-for-symmetry","title":"A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing","date":"2024-10-27","arxiv_id":"2410.20516","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["smsharma/eqnn-jax"],"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"]}}},{"paper":"/paper/bongard-in-wonderland-visual-puzzles-that","slug":"bongard-in-wonderland-visual-puzzles-that","title":"Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?","date":"2024-10-25","arxiv_id":"2410.19546","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ml-research/bongard-in-wonderland"],"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"]}}},{"paper":"/paper/what-if-the-input-is-expanded-in-ood","slug":"what-if-the-input-is-expanded-in-ood","title":"What If the Input is Expanded in OOD Detection?","date":"2024-10-24","arxiv_id":"2410.18472","n_code_links":1,"syntology":{"ran":16,"of":20,"n_ran_checked":9,"n_instrument":7,"unverified":4,"pointer_only":20,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","official":{"repos":["tmlr-group/cover"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/kvsharer-efficient-inference-via-layer-wise","slug":"kvsharer-efficient-inference-via-layer-wise","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","date":"2024-10-24","arxiv_id":"2410.18517","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["yangyifei729/kvsharer"],"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"]}}},{"paper":"/paper/retrieval-augmented-diffusion-models-for-time","slug":"retrieval-augmented-diffusion-models-for-time","title":"Retrieval-Augmented Diffusion Models for Time Series Forecasting","date":"2024-10-24","arxiv_id":"2410.18712","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stanliu96/RATD"],"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"]}}},{"paper":"/paper/should-we-really-edit-language-models-on-the","slug":"should-we-really-edit-language-models-on-the","title":"Should We Really Edit Language Models? On the Evaluation of Edited Language Models","date":"2024-10-24","arxiv_id":"2410.18785","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lqinfdim/editingevaluation"],"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":["found_in_text","official"]}}},{"paper":"/paper/mm-eval-a-multilingual-meta-evaluation","slug":"mm-eval-a-multilingual-meta-evaluation","title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","date":"2024-10-23","arxiv_id":"2410.17578","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["guijinSON/MM-Eval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/graphusion-a-rag-framework-for-knowledge","slug":"graphusion-a-rag-framework-for-knowledge","title":"Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective","date":"2024-10-23","arxiv_id":"2410.17600","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"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","official":{"repos":["irenezihuili/graphusion"],"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"]}}},{"paper":"/paper/blendify-python-rendering-framework-for","slug":"blendify-python-rendering-framework-for","title":"Blendify -- Python rendering framework for Blender","date":"2024-10-23","arxiv_id":"2410.17858","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["ptrvilya/blendify"],"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"]}}},{"paper":"/paper/trustworthy-alignment-of-retrieval-augmented","slug":"trustworthy-alignment-of-retrieval-augmented","title":"Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.16843","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"11 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zmzhang2000/trustworthy-alignment"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/voicebench-benchmarking-llm-based-voice","slug":"voicebench-benchmarking-llm-based-voice","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","date":"2024-10-22","arxiv_id":"2410.17196","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["matthewcym/voicebench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-if-benchmarking-llms-on-multi-turn-and","slug":"multi-if-benchmarking-llms-on-multi-turn-and","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","date":"2024-10-21","arxiv_id":"2410.15553","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/Multi-IF"],"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"]}}},{"paper":"/paper/talos-enhancing-semantic-scene-completion-via","slug":"talos-enhancing-semantic-scene-completion-via","title":"TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight","date":"2024-10-21","arxiv_id":"2410.15674","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":11,"n_instrument":3,"unverified":3,"pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["blue-531/talos"],"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"]}}},{"paper":"/paper/on-conditional-diffusion-models-for-pde","slug":"on-conditional-diffusion-models-for-pde","title":"On conditional diffusion models for PDE simulations","date":"2024-10-21","arxiv_id":"2410.16415","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cambridge-mlg/pdediff"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/are-llms-good-zero-shot-fallacy-classifiers","slug":"are-llms-good-zero-shot-fallacy-classifiers","title":"Are LLMs Good Zero-Shot Fallacy Classifiers?","date":"2024-10-19","arxiv_id":"2410.15050","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["panfjcharlotte98/fallacy_detection"],"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"]}}},{"paper":"/paper/multichartqa-benchmarking-vision-language","slug":"multichartqa-benchmarking-vision-language","title":"MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems","date":"2024-10-18","arxiv_id":"2410.14179","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":5,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zivenzhu/multi-chart-qa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/toward-generalizing-visual-brain-decoding-to","slug":"toward-generalizing-visual-brain-decoding-to","title":"Toward Generalizing Visual Brain Decoding to Unseen Subjects","date":"2024-10-18","arxiv_id":"2410.14445","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":3,"n_instrument":3,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["xiangtaokong/tgbd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-lingual-auto-evaluation-for-assessing","slug":"cross-lingual-auto-evaluation-for-assessing","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","date":"2024-10-17","arxiv_id":"2410.13394","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai4bharat/cia"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/loldu-low-rank-adaptation-via-lower-diag","slug":"loldu-low-rank-adaptation-via-lower-diag","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","date":"2024-10-17","arxiv_id":"2410.13618","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skddj/loldu"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/analyzing-deep-transformer-models-for-time","slug":"analyzing-deep-transformer-models-for-time","title":"Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning","date":"2024-10-17","arxiv_id":"2410.13792","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["azencot-group/gatlm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mitigating-the-backdoor-effect-for-multi-task","slug":"mitigating-the-backdoor-effect-for-multi-task","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","date":"2024-10-17","arxiv_id":"2410.13910","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yangjinluan/dam"],"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"]}}},{"paper":"/paper/catch-channel-aware-multivariate-time-series","slug":"catch-channel-aware-multivariate-time-series","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","date":"2024-10-16","arxiv_id":"2410.12261","n_code_links":1,"syntology":{"ran":11,"of":19,"n_ran_checked":7,"n_instrument":4,"unverified":8,"pointer_only":19,"phrase":"11 ran (of which 8 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["decisionintelligence/catch"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":8,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/dat-improving-adversarial-robustness-via","slug":"dat-improving-adversarial-robustness-via","title":"DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain","date":"2024-10-16","arxiv_id":"2410.12307","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["Feng-peng-Li/DAT"],"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"]}}},{"paper":"/paper/stylistic-multi-task-analysis-of-ukiyo-e","slug":"stylistic-multi-task-analysis-of-ukiyo-e","title":"Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Prints","date":"2024-10-16","arxiv_id":"2410.12379","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["selinakhan/stylistic-MTL-ukiyoe"],"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"]}}},{"paper":"/paper/judgebench-a-benchmark-for-evaluating-llm","slug":"judgebench-a-benchmark-for-evaluating-llm","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","date":"2024-10-16","arxiv_id":"2410.12784","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ScalerLab/JudgeBench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dual-prototype-evolving-for-test-time","slug":"dual-prototype-evolving-for-test-time","title":"Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models","date":"2024-10-16","arxiv_id":"2410.12790","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhangce01/DPE-CLIP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/msc-sql-multi-sample-critiquing-small","slug":"msc-sql-multi-sample-critiquing-small","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","date":"2024-10-16","arxiv_id":"2410.12916","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"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","official":{"repos":["layer6ai-labs/msc-sql"],"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"]}}},{"paper":"/paper/credal-two-sample-tests-of-epistemic","slug":"credal-two-sample-tests-of-epistemic","title":"Credal Two-Sample Tests of Epistemic Uncertainty","date":"2024-10-16","arxiv_id":"2410.12921","n_code_links":1,"syntology":{"ran":12,"of":12,"n_ran_checked":12,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["chau999/credaltwosampletests"],"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"]}}},{"paper":"/paper/hypothesis-testing-the-circuit-hypothesis-in","slug":"hypothesis-testing-the-circuit-hypothesis-in","title":"Hypothesis Testing the Circuit Hypothesis in LLMs","date":"2024-10-16","arxiv_id":"2410.13032","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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","official":{"repos":["blei-lab/circuitry"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-complete-decomposition-of-kl-error-using","slug":"a-complete-decomposition-of-kl-error-using","title":"A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection","date":"2024-10-15","arxiv_id":"2410.11964","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["EnouenJ/mode-attributing-hierarchy"],"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"]}}},{"paper":"/paper/musetalk-real-time-high-quality-lip","slug":"musetalk-real-time-high-quality-lip","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","date":"2024-10-14","arxiv_id":"2410.10122","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"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) · 1 unverified","official":{"repos":["tmelyralab/musetalk"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/effi-code-unleashing-code-efficiency-in","slug":"effi-code-unleashing-code-efficiency-in","title":"EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning","date":"2024-10-14","arxiv_id":"2410.10209","n_code_links":2,"syntology":{"ran":15,"of":15,"n_ran_checked":15,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huangd1999/effi-code","huangd1999/efficoder"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluating-semantic-variation-in-text-to","slug":"evaluating-semantic-variation-in-text-to","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","date":"2024-10-14","arxiv_id":"2410.10291","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhuxiangru/semvarbench"],"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"]}}},{"paper":"/paper/will-llms-replace-the-encoder-only-models-in","slug":"will-llms-replace-the-encoder-only-models-in","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","date":"2024-10-14","arxiv_id":"2410.10476","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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","official":{"repos":["brownfortress/llms-trc"],"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"]}}},{"paper":"/paper/a-practical-approach-to-causal-inference-over","slug":"a-practical-approach-to-causal-inference-over","title":"A Practical Approach to Causal Inference over Time","date":"2024-10-14","arxiv_id":"2410.10502","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["marti5ini/ci-over-time"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/get-rid-of-task-isolation-a-continuous-multi","slug":"get-rid-of-task-isolation-a-continuous-multi","title":"Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework","date":"2024-10-14","arxiv_id":"2410.10524","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dilab-ustcsz/cmust"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unimatch-v2-pushing-the-limit-of-semi","slug":"unimatch-v2-pushing-the-limit-of-semi","title":"UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation","date":"2024-10-14","arxiv_id":"2410.10777","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["LiheYoung/UniMatch-V2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/duoattention-efficient-long-context-llm","slug":"duoattention-efficient-long-context-llm","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","date":"2024-10-14","arxiv_id":"2410.10819","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mit-han-lab/duo-attention"],"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"]}}},{"paper":"/paper/varying-shades-of-wrong-aligning-llms-with","slug":"varying-shades-of-wrong-aligning-llms-with","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","date":"2024-10-14","arxiv_id":"2410.11055","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["yaojh18/Varying-Shades-of-Wrong"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mirage-evaluating-and-explaining-inductive","slug":"mirage-evaluating-and-explaining-inductive","title":"MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models","date":"2024-10-12","arxiv_id":"2410.09542","n_code_links":0,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/reinforcement-learning-for-control-of-non","slug":"reinforcement-learning-for-control-of-non","title":"Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics","date":"2024-10-11","arxiv_id":"2410.08439","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["JacobHA/RL4Dosing"],"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"]}}},{"paper":"/paper/refusal-trained-llms-are-easily-jailbroken-as","slug":"refusal-trained-llms-are-easily-jailbroken-as","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","date":"2024-10-11","arxiv_id":"2410.13886","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["scaleapi/browser-art"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-curriculum-expert-iteration-for","slug":"automatic-curriculum-expert-iteration-for","title":"Automatic Curriculum Expert Iteration for Reliable LLM Reasoning","date":"2024-10-10","arxiv_id":"2410.07627","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salesforceairesearch/auto-cei"],"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"]}}},{"paper":"/paper/macpo-weak-to-strong-alignment-via-multi","slug":"macpo-weak-to-strong-alignment-via-multi","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","date":"2024-10-10","arxiv_id":"2410.07672","n_code_links":0,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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","official":null}},{"paper":"/paper/relational-diffusion-distillation-for","slug":"relational-diffusion-distillation-for","title":"Relational Diffusion Distillation for Efficient Image Generation","date":"2024-10-10","arxiv_id":"2410.07679","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":1,"n_instrument":5,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cantbebetter2/rdd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/minorityprompt-text-to-minority-image","slug":"minorityprompt-text-to-minority-image","title":"Minority-Focused Text-to-Image Generation via Prompt Optimization","date":"2024-10-10","arxiv_id":"2410.07838","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":3,"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","official":{"repos":["anonymous5293/minorityprompt"],"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"]}}},{"paper":"/paper/benchmarking-agentic-workflow-generation","slug":"benchmarking-agentic-workflow-generation","title":"Benchmarking Agentic Workflow Generation","date":"2024-10-10","arxiv_id":"2410.07869","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjunlp/worfbench"],"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"]}}},{"paper":"/paper/compl-ai-framework-a-technical-interpretation","slug":"compl-ai-framework-a-technical-interpretation","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","date":"2024-10-10","arxiv_id":"2410.07959","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["compl-ai/compl-ai"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficiently-learning-at-test-time-active-fine","slug":"efficiently-learning-at-test-time-active-fine","title":"Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs","date":"2024-10-10","arxiv_id":"2410.08020","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["jonhue/activeft"],"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"]}}},{"paper":"/paper/reward-augmented-data-enhances-direct","slug":"reward-augmented-data-enhances-direct","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","date":"2024-10-10","arxiv_id":"2410.08067","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shenao-zhang/reward-augmented-preference"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-ai-generated-text-detection-by","slug":"robust-ai-generated-text-detection-by","title":"Robust AI-Generated Text Detection by Restricted Embeddings","date":"2024-10-10","arxiv_id":"2410.08113","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["silversolver/robustatd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/vibecheck-discover-and-quantify-qualitative","slug":"vibecheck-discover-and-quantify-qualitative","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","date":"2024-10-10","arxiv_id":"2410.12851","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lisadunlap/vibecheck"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-legal-case-retrieval-via-scaling","slug":"enhancing-legal-case-retrieval-via-scaling","title":"Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs","date":"2024-10-09","arxiv_id":"2410.06581","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":12,"n_instrument":2,"unverified":3,"pointer_only":2,"phrase":"14 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["thunlp/lead"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/task-oriented-time-series-imputation","slug":"task-oriented-time-series-imputation","title":"Task-oriented Time Series Imputation Evaluation via Generalized Representers","date":"2024-10-09","arxiv_id":"2410.06652","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["hkuedl/Task-Oriented-Imputation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mitigating-the-language-mismatch-and","slug":"mitigating-the-language-mismatch-and","title":"Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing","date":"2024-10-09","arxiv_id":"2410.07054","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":12,"n_instrument":1,"unverified":4,"pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["weichuanw/llm-based-mt-via-model-editing"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-initialization-to-rule-them-all-fine","slug":"one-initialization-to-rule-them-all-fine","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","date":"2024-10-09","arxiv_id":"2410.07170","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["BenediktAlkin/vtab1k-pytorch","ml-jku/EVA"],"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"]}}},{"paper":"/paper/moe-accelerating-mixture-of-experts-methods","slug":"moe-accelerating-mixture-of-experts-methods","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","date":"2024-10-09","arxiv_id":"2410.07348","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["skyworkai/moe-plus-plus"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/llm-embeddings-improve-test-time-adaptation","slug":"llm-embeddings-improve-test-time-adaptation","title":"LLM Embeddings Improve Test-time Adaptation to Tabular $Y|X$-Shifts","date":"2024-10-09","arxiv_id":"2410.07395","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":1,"n_instrument":5,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["namkoong-lab/llm-tabular-shifts"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/t2v-turbo-v2-enhancing-video-generation-model","slug":"t2v-turbo-v2-enhancing-video-generation-model","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","date":"2024-10-08","arxiv_id":"2410.05677","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/quadratic-is-not-what-you-need-for-multimodal","slug":"quadratic-is-not-what-you-need-for-multimodal","title":"Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See","date":"2024-10-08","arxiv_id":"2410.06169","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":2,"n_instrument":6,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ZhangAIPI/YOPO_MLLM_Pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/entering-real-social-world-benchmarking-the","slug":"entering-real-social-world-benchmarking-the","title":"Entering Real Social World! Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","date":"2024-10-08","arxiv_id":"2410.06195","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gyhou123/egosocialarena"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-fourier-modelling-a-highly-compact","slug":"neural-fourier-modelling-a-highly-compact","title":"Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis","date":"2024-10-07","arxiv_id":"2410.04703","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minkiml/NFM"],"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"]}}},{"paper":"/paper/fast-training-of-sinusoidal-neural-fields-via","slug":"fast-training-of-sinusoidal-neural-fields-via","title":"Fast Training of Sinusoidal Neural Fields via Scaling Initialization","date":"2024-10-07","arxiv_id":"2410.04779","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"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","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"]}}},{"paper":"/paper/unitary-convolutions-for-learning-on-graphs","slug":"unitary-convolutions-for-learning-on-graphs","title":"Unitary convolutions for learning on graphs and groups","date":"2024-10-07","arxiv_id":"2410.05499","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Weber-GeoML/Unitary_Convolutions"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-grained-prediction-of-reading","slug":"fine-grained-prediction-of-reading","title":"Fine-Grained Prediction of Reading Comprehension from Eye Movements","date":"2024-10-06","arxiv_id":"2410.04484","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":{"repos":["lacclab/Reading-Comprehension-Prediction"],"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"]}}},{"paper":"/paper/neuron-level-sequential-editing-for-large","slug":"neuron-level-sequential-editing-for-large","title":"Neuron-Level Sequential Editing for Large Language Models","date":"2024-10-05","arxiv_id":"2410.04045","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":7,"phrase":"7 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jianghoucheng/nse"],"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"]}}},{"paper":"/paper/longgenbench-long-context-generation","slug":"longgenbench-long-context-generation","title":"LongGenBench: Long-context Generation Benchmark","date":"2024-10-05","arxiv_id":"2410.04199","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dominic789654/longgenbench"],"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","unlocated"]}}},{"paper":"/paper/x-alma-plug-play-modules-and-adaptive","slug":"x-alma-plug-play-modules-and-adaptive","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","date":"2024-10-04","arxiv_id":"2410.03115","n_code_links":0,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/graphcroc-cross-correlation-autoencoder-for","slug":"graphcroc-cross-correlation-autoencoder-for","title":"GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction","date":"2024-10-04","arxiv_id":"2410.03396","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":10,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sjduan/graphcroc"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":6,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/personalsum-a-user-subjective-guided","slug":"personalsum-a-user-subjective-guided","title":"PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models","date":"2024-10-04","arxiv_id":"2410.03905","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["smartmediaai/personalsum"],"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"]}}},{"paper":"/paper/model-developmental-safety-a-safety-centric","slug":"model-developmental-safety-a-safety-centric","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","date":"2024-10-04","arxiv_id":"2410.03955","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":1,"n_instrument":4,"unverified":4,"pointer_only":9,"phrase":"5 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; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ganglii/devsafety"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/correlation-and-navigation-in-the-vocabulary","slug":"correlation-and-navigation-in-the-vocabulary","title":"Correlation and Navigation in the Vocabulary Key Representation Space of Language Models","date":"2024-10-03","arxiv_id":"2410.02284","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["KomeijiForce/KeyNavi"],"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"]}}},{"paper":"/paper/unleashing-the-potential-of-the-diffusion","slug":"unleashing-the-potential-of-the-diffusion","title":"Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation","date":"2024-10-03","arxiv_id":"2410.02369","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aim-uofa/diffews"],"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"]}}},{"paper":"/paper/towards-comprehensive-detection-of-chinese","slug":"towards-comprehensive-detection-of-chinese","title":"Towards Comprehensive Detection of Chinese Harmful Memes","date":"2024-10-03","arxiv_id":"2410.02378","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dut-lujunyu/toxicn_mm"],"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"]}}},{"paper":"/paper/divscene-benchmarking-lvlms-for-object","slug":"divscene-benchmarking-lvlms-for-object","title":"DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects","date":"2024-10-03","arxiv_id":"2410.02730","n_code_links":1,"syntology":{"ran":15,"of":15,"n_ran_checked":15,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhaowei-wang-nlp/divscene"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unveiling-language-skills-under-circuits","slug":"unveiling-language-skills-under-circuits","title":"Unveiling Language Skills via Path-Level Circuit Discovery","date":"2024-10-02","arxiv_id":"2410.01334","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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","official":{"repos":["zodiark-ch/language-skill-of-llms"],"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"]}}},{"paper":"/paper/codev-bench-how-do-llms-understand-developer","slug":"codev-bench-how-do-llms-understand-developer","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","date":"2024-10-02","arxiv_id":"2410.01353","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["LingmaTongyi/Codev-Bench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/selective-aggregation-for-low-rank-adaptation","slug":"selective-aggregation-for-low-rank-adaptation","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","date":"2024-10-02","arxiv_id":"2410.01463","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["Pengxin-Guo/FedSA-LoRA"],"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"]}}},{"paper":"/paper/positional-attention-out-of-distribution","slug":"positional-attention-out-of-distribution","title":"Positional Attention: Expressivity and Learnability of Algorithmic Computation","date":"2024-10-02","arxiv_id":"2410.01686","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opallab/positional_attention"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-introduction-to-deep-survival-analysis","slug":"an-introduction-to-deep-survival-analysis","title":"An Introduction to Deep Survival Analysis Models for Predicting Time-to-Event Outcomes","date":"2024-10-01","arxiv_id":"2410.01086","n_code_links":2,"syntology":{"ran":20,"of":24,"n_ran_checked":18,"n_instrument":2,"unverified":4,"pointer_only":24,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["georgehc/survival-intro","georgehc/survival-kernets"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-obstruct-few-shot-image","slug":"learning-to-obstruct-few-shot-image","title":"Learning to Obstruct Few-Shot Image Classification over Restricted Classes","date":"2024-09-28","arxiv_id":"2409.19210","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["amberyzheng/LTO"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/automated-conjecturing-in-mathematics-with","slug":"automated-conjecturing-in-mathematics-with","title":"Automated conjecturing in mathematics with \\emph{TxGraffiti}","date":"2024-09-28","arxiv_id":"2409.19379","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["RandyRDavila/TxGraffiti_APP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-croppable-implicit-neural","slug":"towards-croppable-implicit-neural","title":"Towards Croppable Implicit Neural Representations","date":"2024-09-28","arxiv_id":"2409.19472","n_code_links":1,"syntology":{"ran":13,"of":22,"n_ran_checked":13,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"13 ran (of which 1 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) · 9 unverified","official":{"repos":["maorash/local-global-inrs"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":1,"n_ran_no_instrument_failure":13,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-llms-suffer-from-multi-party-hangover-a","slug":"do-llms-suffer-from-multi-party-hangover-a","title":"Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations","date":"2024-09-27","arxiv_id":"2409.18602","n_code_links":1,"syntology":{"ran":12,"of":19,"n_ran_checked":8,"n_instrument":4,"unverified":7,"pointer_only":19,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 7 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["dhfbk/MPH"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-the-power-of-timestamps-for-robust","slug":"rethinking-the-power-of-timestamps-for-robust","title":"Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective","date":"2024-09-27","arxiv_id":"2409.18696","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["ForestsKing/GLAFF"],"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"]}}},{"paper":"/paper/hr-extreme-a-high-resolution-dataset-for","slug":"hr-extreme-a-high-resolution-dataset-for","title":"HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting","date":"2024-09-27","arxiv_id":"2409.18885","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":1,"n_instrument":4,"unverified":4,"pointer_only":9,"phrase":"5 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; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["HuskyNian/HR-Extreme"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/advancing-open-set-domain-generalization","slug":"advancing-open-set-domain-generalization","title":"Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler","date":"2024-09-26","arxiv_id":"2409.17555","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["kpeng9510/ebil-hads"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/extracting-affect-aggregates-from","slug":"extracting-affect-aggregates-from","title":"Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17990","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dess-mannheim/temporal-adapters"],"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"]}}},{"paper":"/paper/holistic-automated-red-teaming-for-large","slug":"holistic-automated-red-teaming-for-large","title":"Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction","date":"2024-09-25","arxiv_id":"2409.16783","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["jc-ryan/holistic_automated_red_teaming"],"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"]}}},{"paper":"/paper/plurals-a-system-for-guiding-llms-via","slug":"plurals-a-system-for-guiding-llms-via","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","date":"2024-09-25","arxiv_id":"2409.17213","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["josh-ashkinaze/plurals"],"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"]}}},{"paper":"/paper/beyond-redundancy-information-aware","slug":"beyond-redundancy-information-aware","title":"Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning","date":"2024-09-25","arxiv_id":"2409.17386","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":3,"n_instrument":2,"unverified":5,"pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zxlearningdeep/infomgf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/looped-transformers-for-length-generalization","slug":"looped-transformers-for-length-generalization","title":"Looped Transformers for Length Generalization","date":"2024-09-24","arxiv_id":"2409.15647","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":14,"n_instrument":0,"unverified":3,"pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["uw-madison-lee-lab/looped-tf"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mmpt-multimodal-prompt-tuning-for-zero-shot","slug":"mmpt-multimodal-prompt-tuning-for-zero-shot","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","date":"2024-09-24","arxiv_id":"2409.15657","n_code_links":2,"syntology":{"ran":16,"of":26,"n_ran_checked":10,"n_instrument":6,"unverified":10,"pointer_only":26,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","official":{"repos":["william-wang618/m2pt","william-wang618/mmpt-emnlp2024"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":10,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":"/paper/moss-enabling-code-driven-evolution-and","slug":"moss-enabling-code-driven-evolution-and","title":"MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents","date":"2024-09-24","arxiv_id":"2409.16120","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ghost-in-moss/ghostos"],"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"]}}},{"paper":"/paper/towards-representation-learning-for-weighting","slug":"towards-representation-learning-for-weighting","title":"Towards Representation Learning for Weighting Problems in Design-Based Causal Inference","date":"2024-09-24","arxiv_id":"2409.16407","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":14,"n_instrument":0,"unverified":2,"pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["oscarclivio/representations_weighting"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/2409-13989","slug":"2409-13989","title":"ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models","date":"2024-09-21","arxiv_id":"2409.13989","n_code_links":1,"syntology":{"ran":17,"of":18,"n_ran_checked":17,"n_instrument":0,"unverified":1,"pointer_only":18,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ustc-starteam/chemeval"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"56b8d4b799da422eb4698e743aa40d898d2d9ad75e037531f179a5583dbc6783","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}