{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/large-language-model/papers/ran/6","list_of":"/task/large-language-model","task":"Large Language Model","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":6,"pages_in_order":9,"rows_per_page":100,"rows":[501,600],"of":801,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/large-language-model/papers/ran/1","prev":"/task/large-language-model/papers/ran/5","next":"/task/large-language-model/papers/ran/7","papers":[{"url":"/paper/verified-multi-step-synthesis-using-large","slug":"verified-multi-step-synthesis-using-large","title":"VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search","date":"2024-02-13","arxiv_id":"2402.08147","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/verified-multi-step-synthesis-using-large#ran","syntology_url":"https://syntology.ai/paper/2402.08147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08147"}},"official":{"repos":["namin/llm-verified-with-monte-carlo-tree-search"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-smith-a-single-image-can-jailbreak-one","slug":"agent-smith-a-single-image-can-jailbreak-one","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","date":"2024-02-13","arxiv_id":"2402.08567","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/agent-smith-a-single-image-can-jailbreak-one#ran","syntology_url":"https://syntology.ai/paper/2402.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08567"}},"official":{"repos":["sail-sg/agent-smith"],"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/prompt-optimization-in-multi-step-tasks","slug":"prompt-optimization-in-multi-step-tasks","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","date":"2024-02-13","arxiv_id":"2402.08702","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/prompt-optimization-in-multi-step-tasks#ran","syntology_url":"https://syntology.ai/paper/2402.08702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08702"}},"official":{"repos":["yongchao98/promst"],"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/graphtranslator-aligning-graph-model-to-large","slug":"graphtranslator-aligning-graph-model-to-large","title":"GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks","date":"2024-02-11","arxiv_id":"2402.07197","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graphtranslator-aligning-graph-model-to-large#ran","syntology_url":"https://syntology.ai/paper/2402.07197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07197"}},"official":{"repos":["alibaba/graphtranslator"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/urbankgent-a-unified-large-language-model","slug":"urbankgent-a-unified-large-language-model","title":"UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction","date":"2024-02-10","arxiv_id":"2402.06861","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/urbankgent-a-unified-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.06861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06861"}},"official":{"repos":["usail-hkust/urbankgent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-sentence-completion-with-a","slug":"language-model-sentence-completion-with-a","title":"Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method","date":"2024-02-09","arxiv_id":"2402.06125","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/language-model-sentence-completion-with-a#ran","syntology_url":"https://syntology.ai/paper/2402.06125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06125"}},"official":{"repos":["joshua-zingale/plug-and-play-rst-ctg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/resumeflow-an-llm-facilitated-pipeline-for","slug":"resumeflow-an-llm-facilitated-pipeline-for","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","date":"2024-02-09","arxiv_id":"2402.06221","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/resumeflow-an-llm-facilitated-pipeline-for#ran","syntology_url":"https://syntology.ai/paper/2402.06221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06221"}},"official":{"repos":["Ztrimus/job-llm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-the-weakness-of-large-language","slug":"understanding-the-weakness-of-large-language","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","date":"2024-02-09","arxiv_id":"2402.06596","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":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/understanding-the-weakness-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.06596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06596"}},"official":{"repos":["androidarenaagent/androidarena"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/editable-scene-simulation-for-autonomous","slug":"editable-scene-simulation-for-autonomous","title":"Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents","date":"2024-02-08","arxiv_id":"2402.05746","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/editable-scene-simulation-for-autonomous#ran","syntology_url":"https://syntology.ai/paper/2402.05746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05746"}},"official":{"repos":["yifanlu0227/chatsim"],"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/sphinx-x-scaling-data-and-parameters-for-a","slug":"sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","date":"2024-02-08","arxiv_id":"2402.05935","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":3,"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/sphinx-x-scaling-data-and-parameters-for-a#ran","syntology_url":"https://syntology.ai/paper/2402.05935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05935"}},"official":{"repos":["alpha-vllm/llama2-accessory"],"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/can-large-language-model-agents-simulate","slug":"can-large-language-model-agents-simulate","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","date":"2024-02-07","arxiv_id":"2402.04559","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/can-large-language-model-agents-simulate#ran","syntology_url":"https://syntology.ai/paper/2402.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04559"}},"official":{"repos":["camel-ai/agent-trust"],"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/apiq-finetuning-of-2-bit-quantized-large","slug":"apiq-finetuning-of-2-bit-quantized-large","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","date":"2024-02-07","arxiv_id":"2402.05147","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/apiq-finetuning-of-2-bit-quantized-large#ran","syntology_url":"https://syntology.ai/paper/2402.05147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05147"}},"official":{"repos":["baohaoliao/apiq"],"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/anytool-self-reflective-hierarchical-agents","slug":"anytool-self-reflective-hierarchical-agents","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","date":"2024-02-06","arxiv_id":"2402.04253","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/anytool-self-reflective-hierarchical-agents#ran","syntology_url":"https://syntology.ai/paper/2402.04253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04253"}},"official":{"repos":["dyabel/anytool"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/jailbreaking-attack-against-multimodal-large","slug":"jailbreaking-attack-against-multimodal-large","title":"Jailbreaking Attack against Multimodal Large Language Model","date":"2024-02-04","arxiv_id":"2402.02309","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jailbreaking-attack-against-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2402.02309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02309"}},"official":{"repos":["abc03570128/jailbreaking-attack-against-multimodal-large-language-model"],"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":["listed","official"]}}},{"url":"/paper/selecting-large-language-model-to-fine-tune","slug":"selecting-large-language-model-to-fine-tune","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","date":"2024-02-04","arxiv_id":"2402.02314","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selecting-large-language-model-to-fine-tune#ran","syntology_url":"https://syntology.ai/paper/2402.02314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02314"}},"official":null}},{"url":"/paper/kicgpt-large-language-model-with-knowledge-in","slug":"kicgpt-large-language-model-with-knowledge-in","title":"KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion","date":"2024-02-04","arxiv_id":"2402.02389","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":1,"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/kicgpt-large-language-model-with-knowledge-in#ran","syntology_url":"https://syntology.ai/paper/2402.02389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02389"}},"official":{"repos":["weiyanbin1999/kicgpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":18,"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) · 5 unverified","sample_list":"/paper/gerea-question-aware-prompt-captions-for#ran","syntology_url":"https://syntology.ai/paper/2402.02503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02503"}},"official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/style-vectors-for-steering-generative-large","slug":"style-vectors-for-steering-generative-large","title":"Style Vectors for Steering Generative Large Language Model","date":"2024-02-02","arxiv_id":"2402.01618","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/style-vectors-for-steering-generative-large#ran","syntology_url":"https://syntology.ai/paper/2402.01618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01618"}},"official":{"repos":["dlr-sc/style-vectors-for-steering-llms"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/magdi-structured-distillation-of-multi-agent","slug":"magdi-structured-distillation-of-multi-agent","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","date":"2024-02-02","arxiv_id":"2402.01620","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magdi-structured-distillation-of-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2402.01620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01620"}},"official":{"repos":["dinobby/magdi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/apiserve-efficient-api-support-for-large","slug":"apiserve-efficient-api-support-for-large","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","date":"2024-02-02","arxiv_id":"2402.01869","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/apiserve-efficient-api-support-for-large#ran","syntology_url":"https://syntology.ai/paper/2402.01869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01869"}},"official":{"repos":["wuklab/infercept"],"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/croissantllm-a-truly-bilingual-french-english","slug":"croissantllm-a-truly-bilingual-french-english","title":"CroissantLLM: A Truly Bilingual French-English Language Model","date":"2024-02-01","arxiv_id":"2402.00786","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/croissantllm-a-truly-bilingual-french-english#ran","syntology_url":"https://syntology.ai/paper/2402.00786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00786"}},"official":{"repos":["manuelfay/llm-data-hub"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/executable-code-actions-elicit-better-llm","slug":"executable-code-actions-elicit-better-llm","title":"Executable Code Actions Elicit Better LLM Agents","date":"2024-02-01","arxiv_id":"2402.01030","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/executable-code-actions-elicit-better-llm#ran","syntology_url":"https://syntology.ai/paper/2402.01030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01030"}},"official":{"repos":["epfllm/megatron-llm","xingyaoww/code-act"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/when-benchmarks-are-targets-revealing-the","slug":"when-benchmarks-are-targets-revealing-the","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","date":"2024-02-01","arxiv_id":"2402.01781","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-benchmarks-are-targets-revealing-the#ran","syntology_url":"https://syntology.ai/paper/2402.01781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01781"}},"official":{"repos":["national-center-for-ai-saudi-arabia/lm-evaluation-harness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-evaluation-via-matrix","slug":"large-language-model-evaluation-via-matrix","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","date":"2024-01-30","arxiv_id":"2401.17139","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-evaluation-via-matrix#ran","syntology_url":"https://syntology.ai/paper/2401.17139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17139"}},"official":{"repos":["waltonfuture/Diff-eRank"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llamp-large-language-model-made-powerful-for","slug":"llamp-large-language-model-made-powerful-for","title":"LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation","date":"2024-01-30","arxiv_id":"2401.17244","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/llamp-large-language-model-made-powerful-for#ran","syntology_url":"https://syntology.ai/paper/2401.17244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17244"}},"official":{"repos":["chiang-yuan/llamp"],"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/contextualization-distillation-from-large","slug":"contextualization-distillation-from-large","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","date":"2024-01-28","arxiv_id":"2402.01729","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contextualization-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2402.01729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01729"}},"official":{"repos":["david-li0406/contextulization-distillation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/l-autoda-leveraging-large-language-models-for","slug":"l-autoda-leveraging-large-language-models-for","title":"L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks","date":"2024-01-27","arxiv_id":"2401.15335","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/l-autoda-leveraging-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.15335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15335"}},"official":{"repos":["pgg3/L-AutoDA"],"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":["listed","official"]}}},{"url":"/paper/deepseek-coder-when-the-large-language-model","slug":"deepseek-coder-when-the-large-language-model","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","date":"2024-01-25","arxiv_id":"2401.14196","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepseek-coder-when-the-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2401.14196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14196"}},"official":{"repos":["deepseek-ai/DeepSeek-Coder"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-large-language-models-write-parallel-code","slug":"can-large-language-models-write-parallel-code","title":"Can Large Language Models Write Parallel Code?","date":"2024-01-23","arxiv_id":"2401.12554","repositories_listed":1,"syntology":{"n":19,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-large-language-models-write-parallel-code#ran","syntology_url":"https://syntology.ai/paper/2401.12554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12554"}},"official":{"repos":["parallelcodefoundry/ParEval"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mastering-text-to-image-diffusion","slug":"mastering-text-to-image-diffusion","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","date":"2024-01-22","arxiv_id":"2401.11708","repositories_listed":1,"syntology":{"n":24,"n_ran":21,"n_constructed":0,"n_ran_checked":12,"n_instrument":9,"n_unverified":3,"n_honours":2,"n_violates":3,"n_no_contract":7,"n_pointer_only":16,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 3 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mastering-text-to-image-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.11708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11708"}},"official":{"repos":["yangling0818/rpg-diffusionmaster"],"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":["found_in_text","official"]}}},{"url":"/paper/tool-lmm-a-large-multi-modal-model-for-tool","slug":"tool-lmm-a-large-multi-modal-model-for-tool","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","date":"2024-01-19","arxiv_id":"2401.10727","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tool-lmm-a-large-multi-modal-model-for-tool#ran","syntology_url":"https://syntology.ai/paper/2401.10727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10727"}},"official":{"repos":["mllm-tool/mllm-tool","tool-lmm/tool-lmm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vlogger-make-your-dream-a-vlog","slug":"vlogger-make-your-dream-a-vlog","title":"Vlogger: Make Your Dream A Vlog","date":"2024-01-17","arxiv_id":"2401.09414","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vlogger-make-your-dream-a-vlog#ran","syntology_url":"https://syntology.ai/paper/2401.09414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09414"}},"official":{"repos":["zhuangshaobin/vlogger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/small-llms-are-weak-tool-learners-a-multi-llm","slug":"small-llms-are-weak-tool-learners-a-multi-llm","title":"Small LLMs Are Weak Tool Learners: A Multi-LLM Agent","date":"2024-01-14","arxiv_id":"2401.07324","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/small-llms-are-weak-tool-learners-a-multi-llm#ran","syntology_url":"https://syntology.ai/paper/2401.07324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07324"}},"official":{"repos":["x-plug/multi-llm-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/modaverse-efficiently-transforming-modalities","slug":"modaverse-efficiently-transforming-modalities","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","date":"2024-01-12","arxiv_id":"2401.06395","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modaverse-efficiently-transforming-modalities#ran","syntology_url":"https://syntology.ai/paper/2401.06395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06395"}},"official":{"repos":["xinke-wang/modaverse"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepseekmoe-towards-ultimate-expert","slug":"deepseekmoe-towards-ultimate-expert","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","date":"2024-01-11","arxiv_id":"2401.06066","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepseekmoe-towards-ultimate-expert#ran","syntology_url":"https://syntology.ai/paper/2401.06066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06066"}},"official":{"repos":["deepseek-ai/deepseek-moe"],"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":["listed","official"]}}},{"url":"/paper/lego-language-enhanced-multi-modal-grounding","slug":"lego-language-enhanced-multi-modal-grounding","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","date":"2024-01-11","arxiv_id":"2401.06071","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lego-language-enhanced-multi-modal-grounding#ran","syntology_url":"https://syntology.ai/paper/2401.06071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06071"}},"official":{"repos":["lzw-lzw/groundinggpt","lzw-lzw/lego"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-diverse-and-high-quality-texts-by","slug":"generating-diverse-and-high-quality-texts-by","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","date":"2024-01-10","arxiv_id":"2401.05054","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generating-diverse-and-high-quality-texts-by#ran","syntology_url":"https://syntology.ai/paper/2401.05054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05054"}},"official":{"repos":["CyberAgentAILab/diverse-mbr"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rewriting-the-code-a-simple-method-for-large","slug":"rewriting-the-code-a-simple-method-for-large","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","date":"2024-01-09","arxiv_id":"2401.04514","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rewriting-the-code-a-simple-method-for-large#ran","syntology_url":"https://syntology.ai/paper/2401.04514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04514"}},"official":{"repos":["alex-haochenli/reco"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-butterfly-effect-of-altering-prompts-how","slug":"the-butterfly-effect-of-altering-prompts-how","title":"The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance","date":"2024-01-08","arxiv_id":"2401.03729","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/the-butterfly-effect-of-altering-prompts-how#ran","syntology_url":"https://syntology.ai/paper/2401.03729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03729"}},"official":{"repos":["abel2code/the_butterfly_effect_of_prompts"],"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-large-language-model-based","slug":"exploring-large-language-model-based","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","date":"2024-01-07","arxiv_id":"2401.03428","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/exploring-large-language-model-based#ran","syntology_url":"https://syntology.ai/paper/2401.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03428"}},"official":{"repos":["melih-unsal/demogpt"],"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/large-language-models-as-visual-cross-domain","slug":"large-language-models-as-visual-cross-domain","title":"VLLaVO: Mitigating Visual Gap through LLMs","date":"2024-01-06","arxiv_id":"2401.03253","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/large-language-models-as-visual-cross-domain#ran","syntology_url":"https://syntology.ai/paper/2401.03253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03253"}},"official":{"repos":["LL-a-VO/VLLaVO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/an-example-of-evolutionary-computation-large","slug":"an-example-of-evolutionary-computation-large","title":"Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model","date":"2024-01-04","arxiv_id":"2401.02051","repositories_listed":6,"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/an-example-of-evolutionary-computation-large#ran","syntology_url":"https://syntology.ai/paper/2401.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02051"}},"official":{"repos":["feiliu36/eoh"],"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/tinygpt-v-efficient-multimodal-large-language","slug":"tinygpt-v-efficient-multimodal-large-language","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones","date":"2023-12-28","arxiv_id":"2312.16862","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tinygpt-v-efficient-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.16862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16862"}},"official":{"repos":["dlyuangod/tinygpt-v"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-far-are-we-from-believable-ai-agents-a","slug":"how-far-are-we-from-believable-ai-agents-a","title":"How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation","date":"2023-12-28","arxiv_id":"2312.17115","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":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/how-far-are-we-from-believable-ai-agents-a#ran","syntology_url":"https://syntology.ai/paper/2312.17115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17115"}},"official":{"repos":["llmconference/emnlp_conference_2024"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-llm-framework-for-long-range-video","slug":"a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","arxiv_id":"2312.17235","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-simple-llm-framework-for-long-range-video#ran","syntology_url":"https://syntology.ai/paper/2312.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17235"}},"official":{"repos":["ceezh/llovi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-improved-baseline-for-reasoning","slug":"an-improved-baseline-for-reasoning","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","date":"2023-12-28","arxiv_id":"2312.17240","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/an-improved-baseline-for-reasoning#ran","syntology_url":"https://syntology.ai/paper/2312.17240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17240"}},"official":null}},{"url":"/paper/drugassist-a-large-language-model-for","slug":"drugassist-a-large-language-model-for","title":"DrugAssist: A Large Language Model for Molecule Optimization","date":"2023-12-28","arxiv_id":"2401.10334","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/drugassist-a-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.10334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10334"}},"official":{"repos":["blazerye/drugassist"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/solar-10-7b-scaling-large-language-models","slug":"solar-10-7b-scaling-large-language-models","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","date":"2023-12-23","arxiv_id":"2312.15166","repositories_listed":2,"syntology":{"n":26,"n_ran":22,"n_constructed":0,"n_ran_checked":17,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/solar-10-7b-scaling-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2312.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15166"}},"official":null}},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lookahead-an-inference-acceleration-framework","slug":"lookahead-an-inference-acceleration-framework","title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","date":"2023-12-20","arxiv_id":"2312.12728","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/lookahead-an-inference-acceleration-framework#ran","syntology_url":"https://syntology.ai/paper/2312.12728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12728"}},"official":{"repos":["alipay/PainlessInferenceAcceleration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-play-starcraft-ii","slug":"large-language-models-play-starcraft-ii","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","date":"2023-12-19","arxiv_id":"2312.11865","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-play-starcraft-ii#ran","syntology_url":"https://syntology.ai/paper/2312.11865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11865"}},"official":{"repos":["histmeisah/large-language-models-play-starcraftii"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-is-enough-in-fine-tuning-pre-trained","slug":"sparse-is-enough-in-fine-tuning-pre-trained","title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","date":"2023-12-19","arxiv_id":"2312.11875","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":1,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sparse-is-enough-in-fine-tuning-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2312.11875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11875"}},"official":{"repos":["song-wx/sift"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/nomiracl-knowing-when-you-don-t-know-for","slug":"nomiracl-knowing-when-you-don-t-know-for","title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","date":"2023-12-18","arxiv_id":"2312.11361","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/nomiracl-knowing-when-you-don-t-know-for#ran","syntology_url":"https://syntology.ai/paper/2312.11361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11361"}},"official":{"repos":["project-miracl/nomiracl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/g-llava-solving-geometric-problem-with-multi","slug":"g-llava-solving-geometric-problem-with-multi","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","date":"2023-12-18","arxiv_id":"2312.11370","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/g-llava-solving-geometric-problem-with-multi#ran","syntology_url":"https://syntology.ai/paper/2312.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11370"}},"official":{"repos":["pipilurj/g-llava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/powerinfer-fast-large-language-model-serving","slug":"powerinfer-fast-large-language-model-serving","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","date":"2023-12-16","arxiv_id":"2312.12456","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/powerinfer-fast-large-language-model-serving#ran","syntology_url":"https://syntology.ai/paper/2312.12456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12456"}},"official":{"repos":["sjtu-ipads/powerinfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tap4llm-table-provider-on-sampling-augmenting","slug":"tap4llm-table-provider-on-sampling-augmenting","title":"TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning","date":"2023-12-14","arxiv_id":"2312.09039","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tap4llm-table-provider-on-sampling-augmenting#ran","syntology_url":"https://syntology.ai/paper/2312.09039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09039"}},"official":null}},{"url":"/paper/holodeck-language-guided-generation-of-3d","slug":"holodeck-language-guided-generation-of-3d","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","date":"2023-12-14","arxiv_id":"2312.09067","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/holodeck-language-guided-generation-of-3d#ran","syntology_url":"https://syntology.ai/paper/2312.09067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09067"}},"official":{"repos":["allenai/Holodeck"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-for-autonomous-driving","slug":"large-language-models-for-autonomous-driving","title":"Personalized Autonomous Driving with Large Language Models: Field Experiments","date":"2023-12-14","arxiv_id":"2312.09397","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/large-language-models-for-autonomous-driving#ran","syntology_url":"https://syntology.ai/paper/2312.09397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09397"}},"official":null}},{"url":"/paper/hallucination-augmented-contrastive-learning","slug":"hallucination-augmented-contrastive-learning","title":"Hallucination Augmented Contrastive Learning for Multimodal Large Language Model","date":"2023-12-12","arxiv_id":"2312.06968","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hallucination-augmented-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2312.06968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06968"}},"official":{"repos":["x-plug/mplug-halowl"],"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/on-diverse-preferences-for-large-language","slug":"on-diverse-preferences-for-large-language","title":"On Diversified Preferences of Large Language Model Alignment","date":"2023-12-12","arxiv_id":"2312.07401","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-diverse-preferences-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.07401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07401"}},"official":{"repos":["dunzeng/more"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/federated-full-parameter-tuning-of-billion","slug":"federated-full-parameter-tuning-of-billion","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","date":"2023-12-11","arxiv_id":"2312.06353","repositories_listed":2,"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/federated-full-parameter-tuning-of-billion#ran","syntology_url":"https://syntology.ai/paper/2312.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06353"}},"official":{"repos":["alibaba/federatedscope"],"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":["named_in_paper"]}}},{"url":"/paper/localized-symbolic-knowledge-distillation-for-1","slug":"localized-symbolic-knowledge-distillation-for-1","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","date":"2023-12-08","arxiv_id":"2312.04837","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/localized-symbolic-knowledge-distillation-for-1#ran","syntology_url":"https://syntology.ai/paper/2312.04837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04837"}},"official":{"repos":["jamespark3922/localized-skd","jamespark3922/lskd"],"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/sparq-attention-bandwidth-efficient-llm","slug":"sparq-attention-bandwidth-efficient-llm","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","date":"2023-12-08","arxiv_id":"2312.04985","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":2,"n_no_contract":0,"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, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sparq-attention-bandwidth-efficient-llm#ran","syntology_url":"https://syntology.ai/paper/2312.04985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04985"}},"official":{"repos":["graphcore-research/llm-inference-research"],"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/llm-as-os-llmao-agents-as-apps-envisioning","slug":"llm-as-os-llmao-agents-as-apps-envisioning","title":"LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem","date":"2023-12-06","arxiv_id":"2312.03815","repositories_listed":5,"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/llm-as-os-llmao-agents-as-apps-envisioning#ran","syntology_url":"https://syntology.ai/paper/2312.03815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03815"}},"official":null}},{"url":"/paper/creative-agents-empowering-agents-with","slug":"creative-agents-empowering-agents-with","title":"Creative Agents: Empowering Agents with Imagination for Creative Tasks","date":"2023-12-05","arxiv_id":"2312.02519","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/creative-agents-empowering-agents-with#ran","syntology_url":"https://syntology.ai/paper/2312.02519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02519"}},"official":{"repos":["pku-rl/creative-agents"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ulma-unified-language-model-alignment-with","slug":"ulma-unified-language-model-alignment-with","title":"ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference","date":"2023-12-05","arxiv_id":"2312.02554","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/ulma-unified-language-model-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2312.02554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02554"}},"official":{"repos":["unified-language-model-alignment/src"],"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/weakly-supervised-detection-of-hallucinations","slug":"weakly-supervised-detection-of-hallucinations","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","date":"2023-12-05","arxiv_id":"2312.02798","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/weakly-supervised-detection-of-hallucinations#ran","syntology_url":"https://syntology.ai/paper/2312.02798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02798"}},"official":{"repos":["Trusted-AI/adversarial-robustness-toolbox"],"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/characterizing-large-language-model-geometry","slug":"characterizing-large-language-model-geometry","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","date":"2023-12-04","arxiv_id":"2312.01648","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":13,"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) · 6 unverified","sample_list":"/paper/characterizing-large-language-model-geometry#ran","syntology_url":"https://syntology.ai/paper/2312.01648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01648"}},"official":{"repos":["randallbalestriero/splinellm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/instructta-instruction-tuned-targeted-attack","slug":"instructta-instruction-tuned-targeted-attack","title":"InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models","date":"2023-12-04","arxiv_id":"2312.01886","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":12,"phrase":"8 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/instructta-instruction-tuned-targeted-attack#ran","syntology_url":"https://syntology.ai/paper/2312.01886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01886"}},"official":{"repos":["xunguangwang/instructta"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-language-models-as-consistent-story","slug":"large-language-models-as-consistent-story","title":"StoryGPT-V: Large Language Models as Consistent Story Visualizers","date":"2023-12-04","arxiv_id":"2312.02252","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":15,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/large-language-models-as-consistent-story#ran","syntology_url":"https://syntology.ai/paper/2312.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02252"}},"official":{"repos":["xiaoqian-shen/StoryGPT-V"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/radialog-a-large-vision-language-model-for","slug":"radialog-a-large-vision-language-model-for","title":"RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance","date":"2023-11-30","arxiv_id":"2311.18681","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/radialog-a-large-vision-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2311.18681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18681"}},"official":{"repos":["chantalmp/radialog"],"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/critiquellm-scaling-llm-as-critic-for","slug":"critiquellm-scaling-llm-as-critic-for","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","date":"2023-11-30","arxiv_id":"2311.18702","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/critiquellm-scaling-llm-as-critic-for#ran","syntology_url":"https://syntology.ai/paper/2311.18702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18702"}},"official":{"repos":["thu-coai/critiquellm"],"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/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","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/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}},"official":{"repos":["tomchen-ctj/OST"],"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/taiwan-llm-bridging-the-linguistic-divide","slug":"taiwan-llm-bridging-the-linguistic-divide","title":"Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model","date":"2023-11-29","arxiv_id":"2311.17487","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/taiwan-llm-bridging-the-linguistic-divide#ran","syntology_url":"https://syntology.ai/paper/2311.17487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17487"}},"official":{"repos":["miulab/taiwan-llama","miulab/taiwan-llm"],"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/war-and-peace-waragent-large-language-model","slug":"war-and-peace-waragent-large-language-model","title":"War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars","date":"2023-11-28","arxiv_id":"2311.17227","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/war-and-peace-waragent-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2311.17227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17227"}},"official":{"repos":["agiresearch/waragent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intercontrol-generate-human-motion","slug":"intercontrol-generate-human-motion","title":"InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint","date":"2023-11-27","arxiv_id":"2311.15864","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/intercontrol-generate-human-motion#ran","syntology_url":"https://syntology.ai/paper/2311.15864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15864"}},"official":{"repos":["zhenzhiwang/intercontrol"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/removing-nsfw-concepts-from-vision-and","slug":"removing-nsfw-concepts-from-vision-and","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","date":"2023-11-27","arxiv_id":"2311.16254","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":7,"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/removing-nsfw-concepts-from-vision-and#ran","syntology_url":"https://syntology.ai/paper/2311.16254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16254"}},"official":{"repos":["aimagelab/safe-clip"],"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/compositional-chain-of-thought-prompting-for","slug":"compositional-chain-of-thought-prompting-for","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","date":"2023-11-27","arxiv_id":"2311.17076","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}},"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dp-opt-make-large-language-model-your-privacy","slug":"dp-opt-make-large-language-model-your-privacy","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","date":"2023-11-27","arxiv_id":"2312.03724","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dp-opt-make-large-language-model-your-privacy#ran","syntology_url":"https://syntology.ai/paper/2312.03724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03724"}},"official":{"repos":["vita-group/dp-opt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/paragraph-to-image-generation-with","slug":"paragraph-to-image-generation-with","title":"Paragraph-to-Image Generation with Information-Enriched Diffusion Model","date":"2023-11-24","arxiv_id":"2311.14284","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/paragraph-to-image-generation-with#ran","syntology_url":"https://syntology.ai/paper/2311.14284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14284"}},"official":{"repos":["weijiawu/paradiffusion"],"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/finme-a-performance-enhanced-large-language","slug":"finme-a-performance-enhanced-large-language","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","date":"2023-11-23","arxiv_id":"2311.13743","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/finme-a-performance-enhanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.13743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13743"}},"official":{"repos":["pipiku915/finmem-llm-stocktrading"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/when-is-off-policy-evaluation-useful-a-data","slug":"when-is-off-policy-evaluation-useful-a-data","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","date":"2023-11-23","arxiv_id":"2311.14110","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-is-off-policy-evaluation-useful-a-data#ran","syntology_url":"https://syntology.ai/paper/2311.14110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14110"}},"official":{"repos":["holarissun/Data-Centric-OPE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-improving-document-understanding-an","slug":"towards-improving-document-understanding-an","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","date":"2023-11-22","arxiv_id":"2311.13194","repositories_listed":1,"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":4,"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/towards-improving-document-understanding-an#ran","syntology_url":"https://syntology.ai/paper/2311.13194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13194"}},"official":{"repos":["harrytea/tgdoc"],"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/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}},"official":{"repos":["brown-palm/Vamos"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lion-empowering-multimodal-large-language","slug":"lion-empowering-multimodal-large-language","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","date":"2023-11-20","arxiv_id":"2311.11860","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":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lion-empowering-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.11860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11860"}},"official":{"repos":["rshaojimmy/jiutian"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-generation-from-human-brain","slug":"language-generation-from-human-brain","title":"Language Generation from Brain Recordings","date":"2023-11-16","arxiv_id":"2311.09889","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-generation-from-human-brain#ran","syntology_url":"https://syntology.ai/paper/2311.09889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09889"}},"official":{"repos":["yeziyi1998/brain-language-generation"],"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/video-llava-learning-united-visual-1","slug":"video-llava-learning-united-visual-1","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","date":"2023-11-16","arxiv_id":"2311.10122","repositories_listed":6,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-llava-learning-united-visual-1#ran","syntology_url":"https://syntology.ai/paper/2311.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10122"}},"official":{"repos":["PKU-YuanGroup/Video-LLaVA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multistage-collaborative-knowledge","slug":"multistage-collaborative-knowledge","title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation","date":"2023-11-15","arxiv_id":"2311.08640","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multistage-collaborative-knowledge#ran","syntology_url":"https://syntology.ai/paper/2311.08640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08640"}},"official":{"repos":["andotalao24/multistage-collaborative-knowledge-distillation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-fit-to-human-reading-times-via","slug":"improving-fit-to-human-reading-times-via","title":"Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the \"right reasons\"?","date":"2023-11-15","arxiv_id":"2311.09325","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/improving-fit-to-human-reading-times-via#ran","syntology_url":"https://syntology.ai/paper/2311.09325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09325"}},"official":{"repos":["TongLiu-github/TemperatureSaling4RTs"],"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/videocon-robust-video-language-alignment-via","slug":"videocon-robust-video-language-alignment-via","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","date":"2023-11-15","arxiv_id":"2311.10111","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":1,"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/videocon-robust-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2311.10111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10111"}},"official":{"repos":["hritikbansal/videocon"],"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/llatrieval-llm-verified-retrieval-for","slug":"llatrieval-llm-verified-retrieval-for","title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","date":"2023-11-14","arxiv_id":"2311.07838","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llatrieval-llm-verified-retrieval-for#ran","syntology_url":"https://syntology.ai/paper/2311.07838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07838"}},"official":{"repos":["beastyz/llm-verified-retrieval"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-audio-captioning-with-audio","slug":"zero-shot-audio-captioning-with-audio","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","date":"2023-11-14","arxiv_id":"2311.08396","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"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) · 4 unverified","sample_list":"/paper/zero-shot-audio-captioning-with-audio#ran","syntology_url":"https://syntology.ai/paper/2311.08396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08396"}},"official":{"repos":["explainableml/zeraucap"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-open-ended-visual-recognition-with","slug":"towards-open-ended-visual-recognition-with","title":"Towards Open-Ended Visual Recognition with Large Language Model","date":"2023-11-14","arxiv_id":"2311.08400","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/towards-open-ended-visual-recognition-with#ran","syntology_url":"https://syntology.ai/paper/2311.08400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08400"}},"official":{"repos":["bytedance/omniscient-model"],"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/magic-benchmarking-large-language-model","slug":"magic-benchmarking-large-language-model","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","date":"2023-11-14","arxiv_id":"2311.08562","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magic-benchmarking-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2311.08562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08562"}},"official":{"repos":["cathyxl/magic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/acid-abstractive-content-based-ids-for","slug":"acid-abstractive-content-based-ids-for","title":"Summarization-Based Document IDs for Generative Retrieval with Language Models","date":"2023-11-14","arxiv_id":"2311.08593","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/acid-abstractive-content-based-ids-for#ran","syntology_url":"https://syntology.ai/paper/2311.08593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08593"}},"official":{"repos":["lihaoxin2020/summarization-based-document-ids-for-generative-retrieval"],"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/sphinx-the-joint-mixing-of-weights-tasks-and","slug":"sphinx-the-joint-mixing-of-weights-tasks-and","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","date":"2023-11-13","arxiv_id":"2311.07575","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":3,"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/sphinx-the-joint-mixing-of-weights-tasks-and#ran","syntology_url":"https://syntology.ai/paper/2311.07575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07575"}},"official":{"repos":["alpha-vllm/llama2-accessory"],"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/cfbenchmark-chinese-financial-assistant","slug":"cfbenchmark-chinese-financial-assistant","title":"CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model","date":"2023-11-10","arxiv_id":"2311.05812","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/cfbenchmark-chinese-financial-assistant#ran","syntology_url":"https://syntology.ai/paper/2311.05812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05812"}},"official":{"repos":["tongjifinlab/cfbenchmark"],"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/follow-up-differential-descriptions-language","slug":"follow-up-differential-descriptions-language","title":"Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification","date":"2023-11-10","arxiv_id":"2311.07593","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/follow-up-differential-descriptions-language#ran","syntology_url":"https://syntology.ai/paper/2311.07593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07593"}},"official":{"repos":["batsresearch/fudd"],"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/deelm-dependency-enhanced-large-language","slug":"deelm-dependency-enhanced-large-language","title":"BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings","date":"2023-11-09","arxiv_id":"2311.05296","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deelm-dependency-enhanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.05296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05296"}},"official":{"repos":["4ai/bellm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"c22c94eee20b6e63f5a5b65e95251bd8eaca299425ba1e3bd931ad1b2e101db7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}