{"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/navigate/papers/ran/1","list_of":"/task/navigate","task":"Navigate","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":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":152,"counts":{"archive_papers_tagged":1982,"with_a_code_link":644,"where_syntology_ran_a_sample":152,"not_listed_spam_title":3,"listed":1979,"listed_where_code_ran":152,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":130,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":130,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/navigate/papers/ran/1","prev":null,"next":"/task/navigate/papers/ran/2","papers":[{"url":"/paper/ai-research-agents-for-machine-learning","slug":"ai-research-agents-for-machine-learning","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","date":"2025-07-03","arxiv_id":"2507.02554","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/ai-research-agents-for-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2507.02554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02554"}},"official":{"repos":["facebookresearch/aira-dojo"],"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/socialeval-evaluating-social-intelligence-of","slug":"socialeval-evaluating-social-intelligence-of","title":"SocialEval: Evaluating Social Intelligence of Large Language Models","date":"2025-06-01","arxiv_id":"2506.00900","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/socialeval-evaluating-social-intelligence-of#ran","syntology_url":"https://syntology.ai/paper/2506.00900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00900"}},"official":{"repos":["thu-coai/socialeval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in","slug":"when-ethics-and-payoffs-diverge-llm-agents-in","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","date":"2025-05-25","arxiv_id":"2505.19212","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in#ran","syntology_url":"https://syntology.ai/paper/2505.19212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19212"}},"official":{"repos":["sbackmann/moralsim"],"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/webthinker-empowering-large-reasoning-models","slug":"webthinker-empowering-large-reasoning-models","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","date":"2025-04-30","arxiv_id":"2504.21776","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/webthinker-empowering-large-reasoning-models#ran","syntology_url":"https://syntology.ai/paper/2504.21776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21776"}},"official":{"repos":["ruc-nlpir/webthinker","sunnynexus/webthinker"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepresearcher-scaling-deep-research-via","slug":"deepresearcher-scaling-deep-research-via","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","date":"2025-04-04","arxiv_id":"2504.03160","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepresearcher-scaling-deep-research-via#ran","syntology_url":"https://syntology.ai/paper/2504.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03160"}},"official":{"repos":["gair-nlp/deepresearcher"],"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/locagent-graph-guided-llm-agents-for-code","slug":"locagent-graph-guided-llm-agents-for-code","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","date":"2025-03-12","arxiv_id":"2503.09089","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/locagent-graph-guided-llm-agents-for-code#ran","syntology_url":"https://syntology.ai/paper/2503.09089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09089"}},"official":{"repos":["gersteinlab/locagent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-text-to-space-mapping-abstract-spatial","slug":"from-text-to-space-mapping-abstract-spatial","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","date":"2025-02-23","arxiv_id":"2502.16690","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/from-text-to-space-mapping-abstract-spatial#ran","syntology_url":"https://syntology.ai/paper/2502.16690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16690"}},"official":{"repos":["mneuronico/griw-world-spatial-orientation-task"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-solve-the-min-max-mixed-shelves","slug":"learning-to-solve-the-min-max-mixed-shelves","title":"Learning to Solve the Min-Max Mixed-Shelves Picker-Routing Problem via Hierarchical and Parallel Decoding","date":"2025-02-14","arxiv_id":"2502.10233","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-solve-the-min-max-mixed-shelves#ran","syntology_url":"https://syntology.ai/paper/2502.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10233"}},"official":{"repos":["ltluttmann/marl4msprp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/intellagent-a-multi-agent-framework-for","slug":"intellagent-a-multi-agent-framework-for","title":"IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems","date":"2025-01-19","arxiv_id":"2501.11067","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/intellagent-a-multi-agent-framework-for#ran","syntology_url":"https://syntology.ai/paper/2501.11067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11067"}},"official":{"repos":["plurai-ai/intellagent"],"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/precise-fast-and-low-cost-concept-erasure-in","slug":"precise-fast-and-low-cost-concept-erasure-in","title":"Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters","date":"2024-12-09","arxiv_id":"2412.06143","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/precise-fast-and-low-cost-concept-erasure-in#ran","syntology_url":"https://syntology.ai/paper/2412.06143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06143"}},"official":{"repos":["wyuan1001/adavd"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-world-models-for-unconstrained-goal","slug":"learning-world-models-for-unconstrained-goal","title":"Learning World Models for Unconstrained Goal Navigation","date":"2024-11-03","arxiv_id":"2411.02446","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/learning-world-models-for-unconstrained-goal#ran","syntology_url":"https://syntology.ai/paper/2411.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02446"}},"official":{"repos":["RU-Automated-Reasoning-Group/MUN"],"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/personalized-federated-learning-via-feature","slug":"personalized-federated-learning-via-feature","title":"Personalized Federated Learning via Feature Distribution Adaptation","date":"2024-11-01","arxiv_id":"2411.00329","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/personalized-federated-learning-via-feature#ran","syntology_url":"https://syntology.ai/paper/2411.00329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00329"}},"official":{"repos":["cj-mclaughlin/pfedfda"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pcagan-improving-posterior-sampling-cgans-via","slug":"pcagan-improving-posterior-sampling-cgans-via","title":"pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization","date":"2024-11-01","arxiv_id":"2411.00605","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pcagan-improving-posterior-sampling-cgans-via#ran","syntology_url":"https://syntology.ai/paper/2411.00605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00605"}},"official":{"repos":["matt-bendel/pcagan"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-optimization-in-deep-learning","slug":"understanding-optimization-in-deep-learning","title":"Understanding Optimization in Deep Learning with Central Flows","date":"2024-10-31","arxiv_id":"2410.24206","repositories_listed":0,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-optimization-in-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2410.24206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24206"}},"official":null}},{"url":"/paper/infogent-an-agent-based-framework-for-web","slug":"infogent-an-agent-based-framework-for-web","title":"Infogent: An Agent-Based Framework for Web Information Aggregation","date":"2024-10-24","arxiv_id":"2410.19054","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infogent-an-agent-based-framework-for-web#ran","syntology_url":"https://syntology.ai/paper/2410.19054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19054"}},"official":{"repos":["gangiswag/infogent"],"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/entering-real-social-world-benchmarking-the","slug":"entering-real-social-world-benchmarking-the","title":"Entering Real Social World! Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","date":"2024-10-08","arxiv_id":"2410.06195","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/entering-real-social-world-benchmarking-the#ran","syntology_url":"https://syntology.ai/paper/2410.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06195"}},"official":{"repos":["gyhou123/egosocialarena"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/defog-discrete-flow-matching-for-graph","slug":"defog-discrete-flow-matching-for-graph","title":"DeFoG: Discrete Flow Matching for Graph Generation","date":"2024-10-05","arxiv_id":"2410.04263","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/defog-discrete-flow-matching-for-graph#ran","syntology_url":"https://syntology.ai/paper/2410.04263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04263"}},"official":{"repos":["manuelmlmadeira/DeFoG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/event-based-stereo-depth-estimation-a-survey","slug":"event-based-stereo-depth-estimation-a-survey","title":"Event-based Stereo Depth Estimation: A Survey","date":"2024-09-26","arxiv_id":"2409.17680","repositories_listed":2,"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":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/event-based-stereo-depth-estimation-a-survey#ran","syntology_url":"https://syntology.ai/paper/2409.17680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17680"}},"official":null}},{"url":"/paper/revisit-anything-visual-place-recognition-via","slug":"revisit-anything-visual-place-recognition-via","title":"Revisit Anything: Visual Place Recognition via Image Segment Retrieval","date":"2024-09-26","arxiv_id":"2409.18049","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/revisit-anything-visual-place-recognition-via#ran","syntology_url":"https://syntology.ai/paper/2409.18049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18049"}},"official":{"repos":["anyloc/revisit-anything"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/from-commands-to-prompts-llm-based-semantic","slug":"from-commands-to-prompts-llm-based-semantic","title":"From Commands to Prompts: LLM-based Semantic File System for AIOS","date":"2024-09-23","arxiv_id":"2410.11843","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/from-commands-to-prompts-llm-based-semantic#ran","syntology_url":"https://syntology.ai/paper/2410.11843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11843"}},"official":{"repos":["agiresearch/aios-lsfs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flame-learning-to-navigate-with-multimodal","slug":"flame-learning-to-navigate-with-multimodal","title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","date":"2024-08-20","arxiv_id":"2408.11051","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flame-learning-to-navigate-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2408.11051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11051"}},"official":{"repos":["xyz9911/FLAME"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01584","slug":"2408-01584","title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","date":"2024-08-02","arxiv_id":"2408.01584","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-01584#ran","syntology_url":"https://syntology.ai/paper/2408.01584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01584"}},"official":{"repos":["emerge-lab/gpudrive"],"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/stress-testing-long-context-language-models","slug":"stress-testing-long-context-language-models","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","date":"2024-07-23","arxiv_id":"2407.16695","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stress-testing-long-context-language-models#ran","syntology_url":"https://syntology.ai/paper/2407.16695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16695"}},"official":{"repos":["ink-usc/lifelong-icl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/disco-embodied-navigation-and-interaction-via","slug":"disco-embodied-navigation-and-interaction-via","title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","date":"2024-07-20","arxiv_id":"2407.14758","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/disco-embodied-navigation-and-interaction-via#ran","syntology_url":"https://syntology.ai/paper/2407.14758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14758"}},"official":{"repos":["allenxuuu/disco"],"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/human-aware-vision-and-language-navigation","slug":"human-aware-vision-and-language-navigation","title":"Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions","date":"2024-06-27","arxiv_id":"2406.19236","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/human-aware-vision-and-language-navigation#ran","syntology_url":"https://syntology.ai/paper/2406.19236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19236"}},"official":{"repos":["lpercc/ha3d_simulator"],"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":["found_in_text","official"]}}},{"url":"/paper/res-q-evaluating-code-editing-large-language","slug":"res-q-evaluating-code-editing-large-language","title":"RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale","date":"2024-06-24","arxiv_id":"2406.16801","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/res-q-evaluating-code-editing-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16801"}},"official":{"repos":["qurrent-ai/res-q"],"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/indict-code-generation-with-internal","slug":"indict-code-generation-with-internal","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","date":"2024-06-23","arxiv_id":"2407.02518","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/indict-code-generation-with-internal#ran","syntology_url":"https://syntology.ai/paper/2407.02518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02518"}},"official":{"repos":["SalesforceAIResearch/indict_code_gen"],"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/sim-to-real-transfer-via-3d-feature-fields","slug":"sim-to-real-transfer-via-3d-feature-fields","title":"Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation","date":"2024-06-14","arxiv_id":"2406.09798","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sim-to-real-transfer-via-3d-feature-fields#ran","syntology_url":"https://syntology.ai/paper/2406.09798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09798"}},"official":{"repos":["MrZihan/Sim2Real-VLN-3DFF"],"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/gui-odyssey-a-comprehensive-dataset-for-cross","slug":"gui-odyssey-a-comprehensive-dataset-for-cross","title":"GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices","date":"2024-06-12","arxiv_id":"2406.08451","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/gui-odyssey-a-comprehensive-dataset-for-cross#ran","syntology_url":"https://syntology.ai/paper/2406.08451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08451"}},"official":{"repos":["opengvlab/gui-odyssey"],"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/massw-a-new-dataset-and-benchmark-tasks-for","slug":"massw-a-new-dataset-and-benchmark-tasks-for","title":"MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows","date":"2024-06-10","arxiv_id":"2406.06357","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/massw-a-new-dataset-and-benchmark-tasks-for#ran","syntology_url":"https://syntology.ai/paper/2406.06357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06357"}},"official":{"repos":["xingjian-zhang/massw"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/drivlme-enhancing-llm-based-autonomous","slug":"drivlme-enhancing-llm-based-autonomous","title":"DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences","date":"2024-06-05","arxiv_id":"2406.03008","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/drivlme-enhancing-llm-based-autonomous#ran","syntology_url":"https://syntology.ai/paper/2406.03008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03008"}},"official":{"repos":["sled-group/driVLMe"],"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/large-language-models-can-self-improve-at-web","slug":"large-language-models-can-self-improve-at-web","title":"Large Language Models Can Self-Improve At Web Agent Tasks","date":"2024-05-30","arxiv_id":"2405.20309","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/large-language-models-can-self-improve-at-web#ran","syntology_url":"https://syntology.ai/paper/2405.20309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20309"}},"official":{"repos":["AjayP13/webdreamer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/can-graph-learning-improve-task-planning","slug":"can-graph-learning-improve-task-planning","title":"Can Graph Learning Improve Planning in LLM-based Agents?","date":"2024-05-29","arxiv_id":"2405.19119","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-graph-learning-improve-task-planning#ran","syntology_url":"https://syntology.ai/paper/2405.19119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19119"}},"official":{"repos":["wxxshirley/gnn4taskplan"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-guiding-exploration-for-combinatorial","slug":"self-guiding-exploration-for-combinatorial","title":"Self-Guiding Exploration for Combinatorial Problems","date":"2024-05-28","arxiv_id":"2405.17950","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-guiding-exploration-for-combinatorial#ran","syntology_url":"https://syntology.ai/paper/2405.17950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17950"}},"official":{"repos":["zangir/llm-for-cp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multi-level-superoptimizer-for-tensor","slug":"a-multi-level-superoptimizer-for-tensor","title":"Mirage: A Multi-Level Superoptimizer for Tensor Programs","date":"2024-05-09","arxiv_id":"2405.05751","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":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) · 3 unverified","sample_list":"/paper/a-multi-level-superoptimizer-for-tensor#ran","syntology_url":"https://syntology.ai/paper/2405.05751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05751"}},"official":{"repos":["mirage-project/mirage"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fleet-of-agents-coordinated-problem-solving","slug":"fleet-of-agents-coordinated-problem-solving","title":"Fleet of Agents: Coordinated Problem Solving with Large Language Models","date":"2024-05-07","arxiv_id":"2405.06691","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":1,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fleet-of-agents-coordinated-problem-solving#ran","syntology_url":"https://syntology.ai/paper/2405.06691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06691"}},"official":{"repos":["au-clan/foa"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-compression-speeds-up-credit","slug":"sequence-compression-speeds-up-credit","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning","date":"2024-05-06","arxiv_id":"2405.03878","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sequence-compression-speeds-up-credit#ran","syntology_url":"https://syntology.ai/paper/2405.03878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03878"}},"official":{"repos":["aditya-ramesh-10/chunktd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-prism-alignment-project-what","slug":"the-prism-alignment-project-what","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","date":"2024-04-24","arxiv_id":"2404.16019","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-prism-alignment-project-what#ran","syntology_url":"https://syntology.ai/paper/2404.16019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16019"}},"official":{"repos":["hannahkirk/prism-alignment"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/class-level-code-generation-from-natural","slug":"class-level-code-generation-from-natural","title":"Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository","date":"2024-04-22","arxiv_id":"2405.01573","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/class-level-code-generation-from-natural#ran","syntology_url":"https://syntology.ai/paper/2405.01573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01573"}},"official":null}},{"url":"/paper/normad-a-benchmark-for-measuring-the-cultural","slug":"normad-a-benchmark-for-measuring-the-cultural","title":"NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models","date":"2024-04-18","arxiv_id":"2404.12464","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/normad-a-benchmark-for-measuring-the-cultural#ran","syntology_url":"https://syntology.ai/paper/2404.12464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12464"}},"official":{"repos":["akhila-yerukola/normad"],"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/can-vehicle-motion-planning-generalize-to","slug":"can-vehicle-motion-planning-generalize-to","title":"Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?","date":"2024-04-11","arxiv_id":"2404.07569","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/can-vehicle-motion-planning-generalize-to#ran","syntology_url":"https://syntology.ai/paper/2404.07569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07569"}},"official":{"repos":["mh0797/interplan"],"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/oda-observation-driven-agent-for-integrating","slug":"oda-observation-driven-agent-for-integrating","title":"ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs","date":"2024-04-11","arxiv_id":"2404.07677","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":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/oda-observation-driven-agent-for-integrating#ran","syntology_url":"https://syntology.ai/paper/2404.07677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07677"}},"official":{"repos":["lanjiuqing64/kgdata"],"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/goat-bench-a-benchmark-for-multi-modal","slug":"goat-bench-a-benchmark-for-multi-modal","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","date":"2024-04-09","arxiv_id":"2404.06609","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/goat-bench-a-benchmark-for-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2404.06609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06609"}},"official":{"repos":["Ram81/goat-bench"],"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/lookahead-exploration-with-neural-radiance","slug":"lookahead-exploration-with-neural-radiance","title":"Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation","date":"2024-04-02","arxiv_id":"2404.01943","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lookahead-exploration-with-neural-radiance#ran","syntology_url":"https://syntology.ai/paper/2404.01943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01943"}},"official":{"repos":["mrzihan/hnr-vln"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/navcot-boosting-llm-based-vision-and-language","slug":"navcot-boosting-llm-based-vision-and-language","title":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","date":"2024-03-12","arxiv_id":"2403.07376","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/navcot-boosting-llm-based-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2403.07376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07376"}},"official":{"repos":["expectorlin/navcot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ssm-meets-video-diffusion-models-efficient","slug":"ssm-meets-video-diffusion-models-efficient","title":"SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces","date":"2024-03-12","arxiv_id":"2403.07711","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":4,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ssm-meets-video-diffusion-models-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.07711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07711"}},"official":{"repos":["shim0114/ssm-meets-video-diffusion-models"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/why-not-use-your-textbook-knowledge-enhanced","slug":"why-not-use-your-textbook-knowledge-enhanced","title":"Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos","date":"2024-03-05","arxiv_id":"2403.02782","repositories_listed":4,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"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 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/why-not-use-your-textbook-knowledge-enhanced#ran","syntology_url":"https://syntology.ai/paper/2403.02782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02782"}},"official":{"repos":["ravindu-yasas-nagasinghe/kepp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/controllable-preference-optimization-toward","slug":"controllable-preference-optimization-toward","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","date":"2024-02-29","arxiv_id":"2402.19085","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/controllable-preference-optimization-toward#ran","syntology_url":"https://syntology.ai/paper/2402.19085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19085"}},"official":{"repos":["OpenBMB/CPO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-iterative-combinatorial-auction","slug":"understanding-iterative-combinatorial-auction","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","date":"2024-02-29","arxiv_id":"2402.19420","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/understanding-iterative-combinatorial-auction#ran","syntology_url":"https://syntology.ai/paper/2402.19420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19420"}},"official":{"repos":["newmanne/open_spiel"],"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/attacking-llm-watermarks-by-exploiting-their","slug":"attacking-llm-watermarks-by-exploiting-their","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","date":"2024-02-25","arxiv_id":"2402.16187","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":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) · 0 unverified","sample_list":"/paper/attacking-llm-watermarks-by-exploiting-their#ran","syntology_url":"https://syntology.ai/paper/2402.16187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16187"}},"official":{"repos":["qi-pang/llm-watermark-attacks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/instance-aware-exploration-verification","slug":"instance-aware-exploration-verification","title":"Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation","date":"2024-02-25","arxiv_id":"2402.17587","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instance-aware-exploration-verification#ran","syntology_url":"https://syntology.ai/paper/2402.17587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17587"}},"official":{"repos":["xiaohanlei/ieve"],"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/comparing-graph-transformers-via-positional","slug":"comparing-graph-transformers-via-positional","title":"Comparing Graph Transformers via Positional Encodings","date":"2024-02-22","arxiv_id":"2402.14202","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/comparing-graph-transformers-via-positional#ran","syntology_url":"https://syntology.ai/paper/2402.14202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14202"}},"official":{"repos":["blackmit/comparing_graph_transformers_via_positional_encodings"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/openfmnav-towards-open-set-zero-shot-object","slug":"openfmnav-towards-open-set-zero-shot-object","title":"OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models","date":"2024-02-16","arxiv_id":"2402.10670","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openfmnav-towards-open-set-zero-shot-object#ran","syntology_url":"https://syntology.ai/paper/2402.10670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10670"}},"official":{"repos":["yxKryptonite/OpenFMNav"],"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/discovering-sensorimotor-agency-in-cellular","slug":"discovering-sensorimotor-agency-in-cellular","title":"Discovering Sensorimotor Agency in Cellular Automata using Diversity Search","date":"2024-02-14","arxiv_id":"2402.10236","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/discovering-sensorimotor-agency-in-cellular#ran","syntology_url":"https://syntology.ai/paper/2402.10236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10236"}},"official":{"repos":["flowersteam/sensorimotor-lenia-search"],"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/mapping-the-multiverse-of-latent","slug":"mapping-the-multiverse-of-latent","title":"Mapping the Multiverse of Latent Representations","date":"2024-02-02","arxiv_id":"2402.01514","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/mapping-the-multiverse-of-latent#ran","syntology_url":"https://syntology.ai/paper/2402.01514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01514"}},"official":{"repos":["aidos-lab/Presto"],"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/webvln-vision-and-language-navigation-on","slug":"webvln-vision-and-language-navigation-on","title":"WebVLN: Vision-and-Language Navigation on Websites","date":"2023-12-25","arxiv_id":"2312.15820","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"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) · 0 unverified","sample_list":"/paper/webvln-vision-and-language-navigation-on#ran","syntology_url":"https://syntology.ai/paper/2312.15820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15820"}},"official":{"repos":["webvln/webvln"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/appagent-multimodal-agents-as-smartphone","slug":"appagent-multimodal-agents-as-smartphone","title":"AppAgent: Multimodal Agents as Smartphone Users","date":"2023-12-21","arxiv_id":"2312.13771","repositories_listed":2,"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/appagent-multimodal-agents-as-smartphone#ran","syntology_url":"https://syntology.ai/paper/2312.13771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13771"}},"official":{"repos":["mnotgod96/AppAgent"],"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/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/vlfm-vision-language-frontier-maps-for-zero","slug":"vlfm-vision-language-frontier-maps-for-zero","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","date":"2023-12-06","arxiv_id":"2312.03275","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/vlfm-vision-language-frontier-maps-for-zero#ran","syntology_url":"https://syntology.ai/paper/2312.03275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03275"}},"official":{"repos":["bdaiinstitute/vlfm"],"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/dbcopilot-scaling-natural-language-querying","slug":"dbcopilot-scaling-natural-language-querying","title":"DBCopilot: Natural Language Querying over Massive Databases via Schema Routing","date":"2023-12-06","arxiv_id":"2312.03463","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dbcopilot-scaling-natural-language-querying#ran","syntology_url":"https://syntology.ai/paper/2312.03463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03463"}},"official":{"repos":["tshu-w/dbcopilot"],"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/towards-learning-a-generalist-model-for","slug":"towards-learning-a-generalist-model-for","title":"Towards Learning a Generalist Model for Embodied Navigation","date":"2023-12-04","arxiv_id":"2312.02010","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/towards-learning-a-generalist-model-for#ran","syntology_url":"https://syntology.ai/paper/2312.02010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02010"}},"official":{"repos":["lavi-lab/navillm","zd11024/NaviLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tree-of-attacks-jailbreaking-black-box-llms","slug":"tree-of-attacks-jailbreaking-black-box-llms","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","date":"2023-12-04","arxiv_id":"2312.02119","repositories_listed":2,"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/tree-of-attacks-jailbreaking-black-box-llms#ran","syntology_url":"https://syntology.ai/paper/2312.02119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02119"}},"official":{"repos":["ricommunity/tap"],"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/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/advances-in-3d-neural-stylization-a-survey","slug":"advances-in-3d-neural-stylization-a-survey","title":"Advances in 3D Neural Stylization: A Survey","date":"2023-11-30","arxiv_id":"2311.18328","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/advances-in-3d-neural-stylization-a-survey#ran","syntology_url":"https://syntology.ai/paper/2311.18328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18328"}},"official":{"repos":["chenyingshu/advances_3d_neural_stylization"],"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/test-time-adaptive-vision-and-language","slug":"test-time-adaptive-vision-and-language","title":"Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation","date":"2023-11-22","arxiv_id":"2311.13209","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/test-time-adaptive-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2311.13209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13209"}},"official":{"repos":["feliciaxyao/icml2024-fstta"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ml-bench-large-language-models-leverage-open","slug":"ml-bench-large-language-models-leverage-open","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","date":"2023-11-16","arxiv_id":"2311.09835","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/ml-bench-large-language-models-leverage-open#ran","syntology_url":"https://syntology.ai/paper/2311.09835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09835"}},"official":{"repos":["gersteinlab/ml-bench"],"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/navigating-data-heterogeneity-in-federated","slug":"navigating-data-heterogeneity-in-federated","title":"Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection","date":"2023-10-26","arxiv_id":"2310.17097","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/navigating-data-heterogeneity-in-federated#ran","syntology_url":"https://syntology.ai/paper/2310.17097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17097"}},"official":{"repos":["Kthyeon/ssfod"],"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/promptagent-strategic-planning-with-language","slug":"promptagent-strategic-planning-with-language","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization","date":"2023-10-25","arxiv_id":"2310.16427","repositories_listed":2,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/promptagent-strategic-planning-with-language#ran","syntology_url":"https://syntology.ai/paper/2310.16427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16427"}},"official":{"repos":["xinyuanwangcs/promptagent"],"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":["listed","official"]}}},{"url":"/paper/safe-navigation-training-autonomous-vehicles","slug":"safe-navigation-training-autonomous-vehicles","title":"Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA","date":"2023-10-23","arxiv_id":"2311.10735","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/safe-navigation-training-autonomous-vehicles#ran","syntology_url":"https://syntology.ai/paper/2311.10735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10735"}},"official":{"repos":["tejas-deo/safe-navigation-training-autonomous-vehicles-using-deep-reinforcement-learning-in-carla"],"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/can-large-language-models-be-good-path","slug":"can-large-language-models-be-good-path","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","date":"2023-10-05","arxiv_id":"2310.03249","repositories_listed":1,"syntology":{"n":28,"n_ran":28,"n_constructed":0,"n_ran_checked":28,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":28,"n_pointer_only":28,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-large-language-models-be-good-path#ran","syntology_url":"https://syntology.ai/paper/2310.03249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03249"}},"official":{"repos":["mohamedaghzal/llms-as-path-planners"],"state":"official (archive's flag): 28 ran","n_ran":28,"n_constructed":0,"n_ran_no_instrument_failure":28,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-collaboration-mechanisms-for-llm","slug":"exploring-collaboration-mechanisms-for-llm","title":"Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View","date":"2023-10-03","arxiv_id":"2310.02124","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/exploring-collaboration-mechanisms-for-llm#ran","syntology_url":"https://syntology.ai/paper/2310.02124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02124"}},"official":{"repos":["zjunlp/machinesom"],"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/vidchapters-7m-video-chapters-at-scale","slug":"vidchapters-7m-video-chapters-at-scale","title":"VidChapters-7M: Video Chapters at Scale","date":"2023-09-25","arxiv_id":"2309.13952","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":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) · 3 unverified","sample_list":"/paper/vidchapters-7m-video-chapters-at-scale#ran","syntology_url":"https://syntology.ai/paper/2309.13952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13952"}},"official":null}},{"url":"/paper/llm-grounder-open-vocabulary-3d-visual","slug":"llm-grounder-open-vocabulary-3d-visual","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","date":"2023-09-21","arxiv_id":"2309.12311","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":3,"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/llm-grounder-open-vocabulary-3d-visual#ran","syntology_url":"https://syntology.ai/paper/2309.12311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12311"}},"official":{"repos":["sled-group/chat-with-nerf"],"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/reasoning-about-the-unseen-for-efficient","slug":"reasoning-about-the-unseen-for-efficient","title":"Reasoning about the Unseen for Efficient Outdoor Object Navigation","date":"2023-09-18","arxiv_id":"2309.10103","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/reasoning-about-the-unseen-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2309.10103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10103"}},"official":{"repos":["quantingxie/reasonedexplorer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-prompt-evaluation-and-optimization","slug":"offline-prompt-evaluation-and-optimization","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","date":"2023-09-13","arxiv_id":"2309.06553","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/offline-prompt-evaluation-and-optimization#ran","syntology_url":"https://syntology.ai/paper/2309.06553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06553"}},"official":{"repos":["holarissun/prompt-oirl","vanderschaarlab/prompt-oirl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/saynav-grounding-large-language-models-for","slug":"saynav-grounding-large-language-models-for","title":"SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments","date":"2023-09-08","arxiv_id":"2309.04077","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"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) · 0 unverified","sample_list":"/paper/saynav-grounding-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2309.04077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04077"}},"official":{"repos":["arajv/SayNav"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/3d-stmn-dependency-driven-superpoint-text","slug":"3d-stmn-dependency-driven-superpoint-text","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","date":"2023-08-31","arxiv_id":"2308.16632","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/3d-stmn-dependency-driven-superpoint-text#ran","syntology_url":"https://syntology.ai/paper/2308.16632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16632"}},"official":{"repos":["sosppxo/3d-stmn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-reinforcement-learning-training","slug":"improving-reinforcement-learning-training","title":"Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation","date":"2023-08-29","arxiv_id":"2308.14947","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/improving-reinforcement-learning-training#ran","syntology_url":"https://syntology.ai/paper/2308.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14947"}},"official":{"repos":["raise-lab/soc-nav-training"],"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/aerialvln-vision-and-language-navigation-for","slug":"aerialvln-vision-and-language-navigation-for","title":"AerialVLN: Vision-and-Language Navigation for UAVs","date":"2023-08-13","arxiv_id":"2308.06735","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/aerialvln-vision-and-language-navigation-for#ran","syntology_url":"https://syntology.ai/paper/2308.06735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06735"}},"official":{"repos":["airvln/airvln"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bird-s-eye-view-scene-graph-for-vision","slug":"bird-s-eye-view-scene-graph-for-vision","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","date":"2023-08-09","arxiv_id":"2308.04758","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":14,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/bird-s-eye-view-scene-graph-for-vision#ran","syntology_url":"https://syntology.ai/paper/2308.04758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04758"}},"official":{"repos":["defaultrui/bev-scene-graph"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gridmm-grid-memory-map-for-vision-and","slug":"gridmm-grid-memory-map-for-vision-and","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","date":"2023-07-24","arxiv_id":"2307.12907","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gridmm-grid-memory-map-for-vision-and#ran","syntology_url":"https://syntology.ai/paper/2307.12907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12907"}},"official":{"repos":["mrzihan/gridmm"],"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/learning-vision-and-language-navigation-from","slug":"learning-vision-and-language-navigation-from","title":"Learning Vision-and-Language Navigation from YouTube Videos","date":"2023-07-22","arxiv_id":"2307.11984","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"15 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-vision-and-language-navigation-from#ran","syntology_url":"https://syntology.ai/paper/2307.11984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11984"}},"official":{"repos":["jeremylinky/youtube-vln"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/patch-n-pack-navit-a-vision-transformer-for","slug":"patch-n-pack-navit-a-vision-transformer-for","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","date":"2023-07-12","arxiv_id":"2307.06304","repositories_listed":3,"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":2,"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/patch-n-pack-navit-a-vision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2307.06304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06304"}},"official":null}},{"url":"/paper/rl4co-an-extensive-reinforcement-learning-for","slug":"rl4co-an-extensive-reinforcement-learning-for","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","date":"2023-06-29","arxiv_id":"2306.17100","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rl4co-an-extensive-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2306.17100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17100"}},"official":{"repos":["ai4co/rl4co","pytorch/rl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/wizmap-scalable-interactive-visualization-for","slug":"wizmap-scalable-interactive-visualization-for","title":"WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings","date":"2023-06-15","arxiv_id":"2306.09328","repositories_listed":4,"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/wizmap-scalable-interactive-visualization-for#ran","syntology_url":"https://syntology.ai/paper/2306.09328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09328"}},"official":{"repos":["poloclub/wizmap"],"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/generalizable-wireless-navigation-through","slug":"generalizable-wireless-navigation-through","title":"Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning","date":"2023-06-11","arxiv_id":"2306.06766","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/generalizable-wireless-navigation-through#ran","syntology_url":"https://syntology.ai/paper/2306.06766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06766"}},"official":{"repos":["panshark/pirl-win"],"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/baa-ngp-bundle-adjusting-accelerated-neural","slug":"baa-ngp-bundle-adjusting-accelerated-neural","title":"BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives","date":"2023-06-07","arxiv_id":"2306.04166","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/baa-ngp-bundle-adjusting-accelerated-neural#ran","syntology_url":"https://syntology.ai/paper/2306.04166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04166"}},"official":{"repos":["IntelLabs/baa-ngp"],"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/is-a-prompt-and-a-few-samples-all-you-need","slug":"is-a-prompt-and-a-few-samples-all-you-need","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","date":"2023-04-26","arxiv_id":"2304.13861","repositories_listed":2,"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/is-a-prompt-and-a-few-samples-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2304.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13861"}},"official":{"repos":["andersgiovanni/worker_vs_gpt","AGMoller/worker_vs_gpt"],"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/etpnav-evolving-topological-planning-for","slug":"etpnav-evolving-topological-planning-for","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments","date":"2023-04-06","arxiv_id":"2304.03047","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/etpnav-evolving-topological-planning-for#ran","syntology_url":"https://syntology.ai/paper/2304.03047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03047"}},"official":{"repos":["marsaki/etpnav"],"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/kerm-knowledge-enhanced-reasoning-for-vision","slug":"kerm-knowledge-enhanced-reasoning-for-vision","title":"KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation","date":"2023-03-28","arxiv_id":"2303.15796","repositories_listed":1,"syntology":{"n":10,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":9,"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) · 9 unverified","sample_list":"/paper/kerm-knowledge-enhanced-reasoning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2303.15796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15796"}},"official":{"repos":["xiangyangli20/kerm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/sift-sparse-iso-flop-transformations-for","slug":"sift-sparse-iso-flop-transformations-for","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","date":"2023-03-21","arxiv_id":"2303.11525","repositories_listed":2,"syntology":{"n":24,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":2,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sift-sparse-iso-flop-transformations-for#ran","syntology_url":"https://syntology.ai/paper/2303.11525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11525"}},"official":{"repos":["cerebrasresearch/sift","cerebrasresearch/sparse-ift"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/one-4-all-neural-potential-fields-for","slug":"one-4-all-neural-potential-fields-for","title":"One-4-All: Neural Potential Fields for Embodied Navigation","date":"2023-03-07","arxiv_id":"2303.04011","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-4-all-neural-potential-fields-for#ran","syntology_url":"https://syntology.ai/paper/2303.04011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04011"}},"official":null}},{"url":"/paper/hierarchical-generative-adversarial-imitation","slug":"hierarchical-generative-adversarial-imitation","title":"Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments","date":"2023-02-09","arxiv_id":"2302.04823","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/hierarchical-generative-adversarial-imitation#ran","syntology_url":"https://syntology.ai/paper/2302.04823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04823"}},"official":{"repos":["gustavokcouto/hgail"],"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/learning-to-count-isomorphisms-with-graph","slug":"learning-to-count-isomorphisms-with-graph","title":"Learning to Count Isomorphisms with Graph Neural Networks","date":"2023-02-07","arxiv_id":"2302.03266","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"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 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-to-count-isomorphisms-with-graph#ran","syntology_url":"https://syntology.ai/paper/2302.03266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03266"}},"official":{"repos":["Starlien95/Count-GNN"],"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":["official"]}}},{"url":"/paper/evox-a-distributed-gpu-accelerated-library","slug":"evox-a-distributed-gpu-accelerated-library","title":"EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation","date":"2023-01-29","arxiv_id":"2301.12457","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/evox-a-distributed-gpu-accelerated-library#ran","syntology_url":"https://syntology.ai/paper/2301.12457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12457"}},"official":{"repos":["emi-group/evox"],"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/multi-realism-image-compression-with-a","slug":"multi-realism-image-compression-with-a","title":"Multi-Realism Image Compression with a Conditional Generator","date":"2022-12-28","arxiv_id":"2212.13824","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-realism-image-compression-with-a#ran","syntology_url":"https://syntology.ai/paper/2212.13824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13824"}},"official":null}},{"url":"/paper/evaluating-long-term-memory-in-3d-mazes","slug":"evaluating-long-term-memory-in-3d-mazes","title":"Evaluating Long-Term Memory in 3D Mazes","date":"2022-10-24","arxiv_id":"2210.13383","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-long-term-memory-in-3d-mazes#ran","syntology_url":"https://syntology.ai/paper/2210.13383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13383"}},"official":{"repos":["jurgisp/memory-maze"],"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/avalon-a-benchmark-for-rl-generalization","slug":"avalon-a-benchmark-for-rl-generalization","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","date":"2022-10-24","arxiv_id":"2210.13417","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/avalon-a-benchmark-for-rl-generalization#ran","syntology_url":"https://syntology.ai/paper/2210.13417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13417"}},"official":null}},{"url":"/paper/local-bayesian-optimization-via-maximizing","slug":"local-bayesian-optimization-via-maximizing","title":"Local Bayesian optimization via maximizing probability of descent","date":"2022-10-21","arxiv_id":"2210.11662","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/local-bayesian-optimization-via-maximizing#ran","syntology_url":"https://syntology.ai/paper/2210.11662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11662"}},"official":{"repos":["kayween/local-bo-mpd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/near-optimal-multi-agent-learning-for-safe","slug":"near-optimal-multi-agent-learning-for-safe","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","date":"2022-10-12","arxiv_id":"2210.06380","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/near-optimal-multi-agent-learning-for-safe#ran","syntology_url":"https://syntology.ai/paper/2210.06380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06380"}},"official":{"repos":["manish-pra/safemac"],"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"]}}}],"record_sha256":"9d0daa53d3abc57a7cbbcb5466ade2891c3cdfd73a2962d34c68b89ffce4f2e0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}