{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling/papers/ran/3","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":3,"pages_in_order":19,"rows_per_page":100,"rows":[201,300],"of":1894,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modeling/papers/ran/1","prev":"/task/language-modeling/papers/ran/2","next":"/task/language-modeling/papers/ran/4","papers":[{"url":"/paper/dart-eval-a-comprehensive-dna-language-model","slug":"dart-eval-a-comprehensive-dna-language-model","title":"DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA","date":"2024-12-06","arxiv_id":"2412.05430","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":16,"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) · 5 unverified","sample_list":"/paper/dart-eval-a-comprehensive-dna-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.05430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05430"}},"official":{"repos":["kundajelab/dart-eval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"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/understanding-hidden-computations-in-chain-of","slug":"understanding-hidden-computations-in-chain-of","title":"Understanding Hidden Computations in Chain-of-Thought Reasoning","date":"2024-12-05","arxiv_id":"2412.04537","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/understanding-hidden-computations-in-chain-of#ran","syntology_url":"https://syntology.ai/paper/2412.04537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04537"}},"official":{"repos":["rokosbasilisk/filler_tokens"],"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/paligemma-2-a-family-of-versatile-vlms-for","slug":"paligemma-2-a-family-of-versatile-vlms-for","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","date":"2024-12-04","arxiv_id":"2412.03555","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paligemma-2-a-family-of-versatile-vlms-for#ran","syntology_url":"https://syntology.ai/paper/2412.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03555"}},"official":null}},{"url":"/paper/flair-vlm-with-fine-grained-language-informed","slug":"flair-vlm-with-fine-grained-language-informed","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","date":"2024-12-04","arxiv_id":"2412.03561","repositories_listed":2,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":20,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/flair-vlm-with-fine-grained-language-informed#ran","syntology_url":"https://syntology.ai/paper/2412.03561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03561"}},"official":{"repos":["explainableml/flair"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-language-models-as-synthetic-data","slug":"evaluating-language-models-as-synthetic-data","title":"Evaluating Language Models as Synthetic Data Generators","date":"2024-12-04","arxiv_id":"2412.03679","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":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) · 4 unverified","sample_list":"/paper/evaluating-language-models-as-synthetic-data#ran","syntology_url":"https://syntology.ai/paper/2412.03679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03679"}},"official":{"repos":["neulab/data-agora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/from-language-models-over-tokens-to-language","slug":"from-language-models-over-tokens-to-language","title":"From Language Models over Tokens to Language Models over Characters","date":"2024-12-04","arxiv_id":"2412.03719","repositories_listed":0,"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/from-language-models-over-tokens-to-language#ran","syntology_url":"https://syntology.ai/paper/2412.03719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03719"}},"official":null}},{"url":"/paper/glm-4-voice-towards-intelligent-and-human","slug":"glm-4-voice-towards-intelligent-and-human","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","date":"2024-12-03","arxiv_id":"2412.02612","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/glm-4-voice-towards-intelligent-and-human#ran","syntology_url":"https://syntology.ai/paper/2412.02612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02612"}},"official":{"repos":["thudm/glm-4-voice"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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/align-kd-distilling-cross-modal-alignment","slug":"align-kd-distilling-cross-modal-alignment","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model","date":"2024-12-02","arxiv_id":"2412.01282","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/align-kd-distilling-cross-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2412.01282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01282"}},"official":{"repos":["fqhank/align-kd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/mba-rag-a-bandit-approach-for-adaptive","slug":"mba-rag-a-bandit-approach-for-adaptive","title":"MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity","date":"2024-12-02","arxiv_id":"2412.01572","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/mba-rag-a-bandit-approach-for-adaptive#ran","syntology_url":"https://syntology.ai/paper/2412.01572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01572"}},"official":{"repos":["futureeeeee/mba"],"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/cls-attention-is-all-you-need-for-training","slug":"cls-attention-is-all-you-need-for-training","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","date":"2024-12-02","arxiv_id":"2412.01818","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cls-attention-is-all-you-need-for-training#ran","syntology_url":"https://syntology.ai/paper/2412.01818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01818"}},"official":{"repos":["theia-4869/fastervlm","theia-4869/vispruner"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/prompthsi-universal-hyperspectral-image","slug":"prompthsi-universal-hyperspectral-image","title":"PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation","date":"2024-11-24","arxiv_id":"2411.15922","repositories_listed":1,"syntology":{"n":17,"n_ran":17,"n_constructed":0,"n_ran_checked":12,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompthsi-universal-hyperspectral-image#ran","syntology_url":"https://syntology.ai/paper/2411.15922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15922"}},"official":{"repos":["chingheng0808/PromptHSI"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/steering-away-from-harm-an-adaptive-approach","slug":"steering-away-from-harm-an-adaptive-approach","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","date":"2024-11-23","arxiv_id":"2411.16721","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/steering-away-from-harm-an-adaptive-approach#ran","syntology_url":"https://syntology.ai/paper/2411.16721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16721"}},"official":{"repos":["ASTRAL-Group/ASTRA"],"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/textit-revelio-interpreting-and-leveraging","slug":"textit-revelio-interpreting-and-leveraging","title":"$\\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models","date":"2024-11-23","arxiv_id":"2411.16725","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":1,"n_no_contract":3,"n_pointer_only":4,"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","sample_list":"/paper/textit-revelio-interpreting-and-leveraging#ran","syntology_url":"https://syntology.ai/paper/2411.16725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16725"}},"official":{"repos":["revelio-diffusion/revelio"],"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","unlocated"]}}},{"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/re-bench-evaluating-frontier-ai-r-d","slug":"re-bench-evaluating-frontier-ai-r-d","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","date":"2024-11-22","arxiv_id":"2411.15114","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/re-bench-evaluating-frontier-ai-r-d#ran","syntology_url":"https://syntology.ai/paper/2411.15114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15114"}},"official":{"repos":["METR/ai-rd-tasks","wecoai/aideml"],"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/tulu-3-pushing-frontiers-in-open-language","slug":"tulu-3-pushing-frontiers-in-open-language","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","date":"2024-11-22","arxiv_id":"2411.15124","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/tulu-3-pushing-frontiers-in-open-language#ran","syntology_url":"https://syntology.ai/paper/2411.15124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15124"}},"official":{"repos":["allenai/open-instruct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/gmai-vl-gmai-vl-5-5m-a-large-vision-language","slug":"gmai-vl-gmai-vl-5-5m-a-large-vision-language","title":"GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI","date":"2024-11-21","arxiv_id":"2411.14522","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gmai-vl-gmai-vl-5-5m-a-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.14522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14522"}},"official":{"repos":["uni-medical/gmai-vl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unlocking-state-tracking-in-linear-rnns","slug":"unlocking-state-tracking-in-linear-rnns","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","date":"2024-11-19","arxiv_id":"2411.12537","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unlocking-state-tracking-in-linear-rnns#ran","syntology_url":"https://syntology.ai/paper/2411.12537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12537"}},"official":{"repos":["automl/unlocking_state_tracking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-attention-enhancing-transformer","slug":"selective-attention-enhancing-transformer","title":"Selective Attention: Enhancing Transformer through Principled Context Control","date":"2024-11-19","arxiv_id":"2411.12892","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/selective-attention-enhancing-transformer#ran","syntology_url":"https://syntology.ai/paper/2411.12892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12892"}},"official":{"repos":["umich-sota/selective_attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mc-llava-multi-concept-personalized-vision","slug":"mc-llava-multi-concept-personalized-vision","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","date":"2024-11-18","arxiv_id":"2411.11706","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mc-llava-multi-concept-personalized-vision#ran","syntology_url":"https://syntology.ai/paper/2411.11706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11706"}},"official":{"repos":["arctanxarc/mc-llava"],"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","unlocated"]}}},{"url":"/paper/vl-uncertainty-detecting-hallucination-in","slug":"vl-uncertainty-detecting-hallucination-in","title":"VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation","date":"2024-11-18","arxiv_id":"2411.11919","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vl-uncertainty-detecting-hallucination-in#ran","syntology_url":"https://syntology.ai/paper/2411.11919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11919"}},"official":null}},{"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/metala-unified-optimal-linear-approximation","slug":"metala-unified-optimal-linear-approximation","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","date":"2024-11-16","arxiv_id":"2411.10741","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/metala-unified-optimal-linear-approximation#ran","syntology_url":"https://syntology.ai/paper/2411.10741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10741"}},"official":{"repos":["BICLab/MetaLA"],"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/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/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/separating-tongue-from-thought-activation","slug":"separating-tongue-from-thought-activation","title":"Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers","date":"2024-11-13","arxiv_id":"2411.08745","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/separating-tongue-from-thought-activation#ran","syntology_url":"https://syntology.ai/paper/2411.08745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08745"}},"official":{"repos":["butanium/llm-lang-agnostic"],"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/model-fusion-through-bayesian-optimization-in","slug":"model-fusion-through-bayesian-optimization-in","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","date":"2024-11-11","arxiv_id":"2411.06710","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/model-fusion-through-bayesian-optimization-in#ran","syntology_url":"https://syntology.ai/paper/2411.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06710"}},"official":{"repos":["chaeyoon-jang/bomf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"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/training-neural-networks-as-recognizers-of","slug":"training-neural-networks-as-recognizers-of","title":"Training Neural Networks as Recognizers of Formal Languages","date":"2024-11-11","arxiv_id":"2411.07107","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-neural-networks-as-recognizers-of#ran","syntology_url":"https://syntology.ai/paper/2411.07107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07107"}},"official":{"repos":["rycolab/flare","rycolab/neural-network-recognizers"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/more-expressive-attention-with-negative","slug":"more-expressive-attention-with-negative","title":"More Expressive Attention with Negative Weights","date":"2024-11-11","arxiv_id":"2411.07176","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/more-expressive-attention-with-negative#ran","syntology_url":"https://syntology.ai/paper/2411.07176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07176"}},"official":{"repos":["trestad/cogattn"],"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","unlocated"]}}},{"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/the-surprising-effectiveness-of-test-time","slug":"the-surprising-effectiveness-of-test-time","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","date":"2024-11-11","arxiv_id":"2411.07279","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-surprising-effectiveness-of-test-time#ran","syntology_url":"https://syntology.ai/paper/2411.07279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07279"}},"official":{"repos":["ekinakyurek/marc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/concept-bottleneck-language-models-for","slug":"concept-bottleneck-language-models-for","title":"Concept Bottleneck Language Models For protein design","date":"2024-11-09","arxiv_id":"2411.06090","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/concept-bottleneck-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2411.06090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06090"}},"official":{"repos":["prescient-design/lobster"],"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/aioli-a-unified-optimization-framework-for","slug":"aioli-a-unified-optimization-framework-for","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","date":"2024-11-08","arxiv_id":"2411.05735","repositories_listed":1,"syntology":{"n":31,"n_ran":23,"n_constructed":3,"n_ran_checked":19,"n_instrument":4,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"23 ran (of which 3 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/aioli-a-unified-optimization-framework-for#ran","syntology_url":"https://syntology.ai/paper/2411.05735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05735"}},"official":{"repos":["hazyresearch/aioli"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":3,"n_ran_no_instrument_failure":19,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-navigation-with-vision-language","slug":"end-to-end-navigation-with-vision-language","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","date":"2024-11-08","arxiv_id":"2411.05755","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/end-to-end-navigation-with-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05755"}},"official":{"repos":["Jirl-upenn/VLMnav"],"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/bendvlm-test-time-debiasing-of-vision","slug":"bendvlm-test-time-debiasing-of-vision","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","date":"2024-11-07","arxiv_id":"2411.04420","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bendvlm-test-time-debiasing-of-vision#ran","syntology_url":"https://syntology.ai/paper/2411.04420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04420"}},"official":{"repos":["waltergerych/bend_vlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/delift-data-efficient-language-model","slug":"delift-data-efficient-language-model","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","date":"2024-11-07","arxiv_id":"2411.04425","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/delift-data-efficient-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.04425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04425"}},"official":{"repos":["agarwalishika/delift"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"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/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/benchmarking-vision-language-model-unlearning","slug":"benchmarking-vision-language-model-unlearning","title":"Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset","date":"2024-11-05","arxiv_id":"2411.03554","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":18,"phrase":"13 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/benchmarking-vision-language-model-unlearning#ran","syntology_url":"https://syntology.ai/paper/2411.03554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03554"}},"official":{"repos":["safolab-wisc/fiubench"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/regress-don-t-guess-a-regression-like-loss-on","slug":"regress-don-t-guess-a-regression-like-loss-on","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","date":"2024-11-04","arxiv_id":"2411.02083","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/regress-don-t-guess-a-regression-like-loss-on#ran","syntology_url":"https://syntology.ai/paper/2411.02083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02083"}},"official":{"repos":["tum-ai/number-token-loss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rule-based-rewards-for-language-model-safety","slug":"rule-based-rewards-for-language-model-safety","title":"Rule Based Rewards for Language Model Safety","date":"2024-11-02","arxiv_id":"2411.01111","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/rule-based-rewards-for-language-model-safety#ran","syntology_url":"https://syntology.ai/paper/2411.01111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01111"}},"official":{"repos":["openai/safety-rbr-code-and-data"],"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/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/lingma-swe-gpt-an-open-development-process","slug":"lingma-swe-gpt-an-open-development-process","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","date":"2024-11-01","arxiv_id":"2411.00622","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":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","sample_list":"/paper/lingma-swe-gpt-an-open-development-process#ran","syntology_url":"https://syntology.ai/paper/2411.00622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00622"}},"official":{"repos":["LingmaTongyi/Lingma-SWE-GPT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/randomized-autoregressive-visual-generation","slug":"randomized-autoregressive-visual-generation","title":"Randomized Autoregressive Visual Generation","date":"2024-11-01","arxiv_id":"2411.00776","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/randomized-autoregressive-visual-generation#ran","syntology_url":"https://syntology.ai/paper/2411.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00776"}},"official":{"repos":["bytedance/1d-tokenizer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/normalization-layer-per-example-gradients-are","slug":"normalization-layer-per-example-gradients-are","title":"Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers","date":"2024-11-01","arxiv_id":"2411.00999","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/normalization-layer-per-example-gradients-are#ran","syntology_url":"https://syntology.ai/paper/2411.00999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00999"}},"official":{"repos":["cerebrasresearch/nanogns"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-wrong-with-perplexity-for-long","slug":"what-is-wrong-with-perplexity-for-long","title":"What is Wrong with Perplexity for Long-context Language Modeling?","date":"2024-10-31","arxiv_id":"2410.23771","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/what-is-wrong-with-perplexity-for-long#ran","syntology_url":"https://syntology.ai/paper/2410.23771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23771"}},"official":{"repos":["pku-ml/longppl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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/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/gpt-or-bert-why-not-both","slug":"gpt-or-bert-why-not-both","title":"GPT or BERT: why not both?","date":"2024-10-31","arxiv_id":"2410.24159","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/gpt-or-bert-why-not-both#ran","syntology_url":"https://syntology.ai/paper/2410.24159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24159"}},"official":{"repos":["ltgoslo/gpt-bert"],"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/interpretable-language-modeling-via-induction","slug":"interpretable-language-modeling-via-induction","title":"Interpretable Language Modeling via Induction-head Ngram Models","date":"2024-10-31","arxiv_id":"2411.00066","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-language-modeling-via-induction#ran","syntology_url":"https://syntology.ai/paper/2411.00066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00066"}},"official":{"repos":["ejkim47/induction-gram"],"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":["found_in_text","official"]}}},{"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/mutaplm-protein-language-modeling-for","slug":"mutaplm-protein-language-modeling-for","title":"MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering","date":"2024-10-30","arxiv_id":"2410.22949","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mutaplm-protein-language-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2410.22949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22949"}},"official":{"repos":["pharmolix/mutaplm"],"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":["listed","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/comal-a-convergent-meta-algorithm-for","slug":"comal-a-convergent-meta-algorithm-for","title":"COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences","date":"2024-10-30","arxiv_id":"2410.23223","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/comal-a-convergent-meta-algorithm-for#ran","syntology_url":"https://syntology.ai/paper/2410.23223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23223"}},"official":{"repos":["yale-nlp/comal"],"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/f-po-generalizing-preference-optimization","slug":"f-po-generalizing-preference-optimization","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","date":"2024-10-29","arxiv_id":"2410.21662","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":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) · 2 unverified","sample_list":"/paper/f-po-generalizing-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2410.21662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21662"}},"official":{"repos":["minkaixu/fpo"],"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/improving-in-context-learning-with-small","slug":"improving-in-context-learning-with-small","title":"Improving In-Context Learning with Small Language Model Ensembles","date":"2024-10-29","arxiv_id":"2410.21868","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-in-context-learning-with-small#ran","syntology_url":"https://syntology.ai/paper/2410.21868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21868"}},"official":{"repos":["mehdimojarradi/Ensemble-SuperICL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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/abrupt-learning-in-transformers-a-case-study","slug":"abrupt-learning-in-transformers-a-case-study","title":"Abrupt Learning in Transformers: A Case Study on Matrix Completion","date":"2024-10-29","arxiv_id":"2410.22244","repositories_listed":0,"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":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","sample_list":"/paper/abrupt-learning-in-transformers-a-case-study#ran","syntology_url":"https://syntology.ai/paper/2410.22244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22244"}},"official":null}},{"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/graph-based-uncertainty-metrics-for-long-form","slug":"graph-based-uncertainty-metrics-for-long-form","title":"Graph-based Uncertainty Metrics for Long-form Language Model Outputs","date":"2024-10-28","arxiv_id":"2410.20783","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/graph-based-uncertainty-metrics-for-long-form#ran","syntology_url":"https://syntology.ai/paper/2410.20783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20783"}},"official":{"repos":["mingjianjiang-1/graph-based-uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-enhanced-mutation-mastery","slug":"retrieval-enhanced-mutation-mastery","title":"Retrieval-Enhanced Mutation Mastery: Augmenting Zero-Shot Prediction of Protein Language Model","date":"2024-10-28","arxiv_id":"2410.21127","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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","sample_list":"/paper/retrieval-enhanced-mutation-mastery#ran","syntology_url":"https://syntology.ai/paper/2410.21127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21127"}},"official":{"repos":["tyang816/protrem"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/llama-scope-extracting-millions-of-features","slug":"llama-scope-extracting-millions-of-features","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","date":"2024-10-27","arxiv_id":"2410.20526","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":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","sample_list":"/paper/llama-scope-extracting-millions-of-features#ran","syntology_url":"https://syntology.ai/paper/2410.20526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20526"}},"official":{"repos":["openmoss/language-model-saes"],"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/centaur-a-foundation-model-of-human-cognition","slug":"centaur-a-foundation-model-of-human-cognition","title":"Centaur: a foundation model of human cognition","date":"2024-10-26","arxiv_id":"2410.20268","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":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) · 0 unverified","sample_list":"/paper/centaur-a-foundation-model-of-human-cognition#ran","syntology_url":"https://syntology.ai/paper/2410.20268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20268"}},"official":{"repos":["marcelbinz/Llama-3.1-Centaur-70B"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/structure-language-models-for-protein","slug":"structure-language-models-for-protein","title":"Structure Language Models for Protein Conformation Generation","date":"2024-10-24","arxiv_id":"2410.18403","repositories_listed":0,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/structure-language-models-for-protein#ran","syntology_url":"https://syntology.ai/paper/2410.18403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18403"}},"official":null}},{"url":"/paper/scaling-up-masked-diffusion-models-on-text","slug":"scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","arxiv_id":"2410.18514","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/scaling-up-masked-diffusion-models-on-text#ran","syntology_url":"https://syntology.ai/paper/2410.18514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18514"}},"official":{"repos":["ml-gsai/smdm"],"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/cross-model-control-improving-multiple-large","slug":"cross-model-control-improving-multiple-large","title":"Cross-model Control: Improving Multiple Large Language Models in One-time Training","date":"2024-10-23","arxiv_id":"2410.17599","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"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) · 2 unverified","sample_list":"/paper/cross-model-control-improving-multiple-large#ran","syntology_url":"https://syntology.ai/paper/2410.17599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17599"}},"official":{"repos":["wujwyi/cmc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-diffusion-language-models-via","slug":"scaling-diffusion-language-models-via","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","date":"2024-10-23","arxiv_id":"2410.17891","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/scaling-diffusion-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2410.17891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17891"}},"official":{"repos":["hkunlp/diffullama"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/papillon-privacy-preservation-from-internet","slug":"papillon-privacy-preservation-from-internet","title":"PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles","date":"2024-10-22","arxiv_id":"2410.17127","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/papillon-privacy-preservation-from-internet#ran","syntology_url":"https://syntology.ai/paper/2410.17127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17127"}},"official":{"repos":["columbia-nlp-lab/papillon","siyan-sylvia-li/papillon"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/miniplm-knowledge-distillation-for-pre","slug":"miniplm-knowledge-distillation-for-pre","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","date":"2024-10-22","arxiv_id":"2410.17215","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":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) · 3 unverified","sample_list":"/paper/miniplm-knowledge-distillation-for-pre#ran","syntology_url":"https://syntology.ai/paper/2410.17215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17215"}},"official":{"repos":["thu-coai/miniplm"],"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/frontiers-in-intelligent-colonoscopy","slug":"frontiers-in-intelligent-colonoscopy","title":"Frontiers in Intelligent Colonoscopy","date":"2024-10-22","arxiv_id":"2410.17241","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":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) · 3 unverified","sample_list":"/paper/frontiers-in-intelligent-colonoscopy#ran","syntology_url":"https://syntology.ai/paper/2410.17241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17241"}},"official":{"repos":["ai4colonoscopy/intelliscope"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/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/improve-vision-language-model-chain-of","slug":"improve-vision-language-model-chain-of","title":"Improve Vision Language Model Chain-of-thought Reasoning","date":"2024-10-21","arxiv_id":"2410.16198","repositories_listed":2,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":13,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":3,"n_no_contract":10,"n_pointer_only":22,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 3 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/improve-vision-language-model-chain-of#ran","syntology_url":"https://syntology.ai/paper/2410.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16198"}},"official":{"repos":["riflezhang/llava-reasoner-dpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/m-rewardbench-evaluating-reward-models-in","slug":"m-rewardbench-evaluating-reward-models-in","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","date":"2024-10-20","arxiv_id":"2410.15522","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m-rewardbench-evaluating-reward-models-in#ran","syntology_url":"https://syntology.ai/paper/2410.15522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15522"}},"official":{"repos":["for-ai/m-rewardbench"],"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":["listed","official"]}}},{"url":"/paper/montessori-instruct-generate-influential","slug":"montessori-instruct-generate-influential","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","date":"2024-10-18","arxiv_id":"2410.14208","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/montessori-instruct-generate-influential#ran","syntology_url":"https://syntology.ai/paper/2410.14208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14208"}},"official":{"repos":["cxcscmu/montessori-instruct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/snac-multi-scale-neural-audio-codec","slug":"snac-multi-scale-neural-audio-codec","title":"SNAC: Multi-Scale Neural Audio Codec","date":"2024-10-18","arxiv_id":"2410.14411","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/snac-multi-scale-neural-audio-codec#ran","syntology_url":"https://syntology.ai/paper/2410.14411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14411"}},"official":{"repos":["hubertsiuzdak/snac"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-systematic-study-of-cross-layer-kv-sharing","slug":"a-systematic-study-of-cross-layer-kv-sharing","title":"A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference","date":"2024-10-18","arxiv_id":"2410.14442","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-systematic-study-of-cross-layer-kv-sharing#ran","syntology_url":"https://syntology.ai/paper/2410.14442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14442"}},"official":{"repos":["whyNLP/LCKV"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/momentumsmoe-integrating-momentum-into-sparse","slug":"momentumsmoe-integrating-momentum-into-sparse","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","date":"2024-10-18","arxiv_id":"2410.14574","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/momentumsmoe-integrating-momentum-into-sparse#ran","syntology_url":"https://syntology.ai/paper/2410.14574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14574"}},"official":{"repos":["rachtsy/momentumsmoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/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/exploring-the-design-space-of-visual-context","slug":"exploring-the-design-space-of-visual-context","title":"Exploring the Design Space of Visual Context Representation in Video MLLMs","date":"2024-10-17","arxiv_id":"2410.13694","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-the-design-space-of-visual-context#ran","syntology_url":"https://syntology.ai/paper/2410.13694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13694"}},"official":{"repos":["rucaibox/opt-visor"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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"]}}}],"record_sha256":"551a8325c4e0fbf3ee65a018d734bb66993673249b6deae07bba4536349a2022","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}