{"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/imitation-learning/papers/2","list_of":"/task/imitation-learning","task":"Imitation Learning","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":22,"rows_per_page":100,"rows":[101,200],"of":2122,"counts":{"archive_papers_tagged":2122,"with_a_code_link":691,"where_syntology_ran_a_sample":234,"not_listed_spam_title":0,"listed":2122,"listed_where_code_ran":234,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":191,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":191,"listed_every_run_a_failure_of_syntologys_instrument":43,"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/imitation-learning","prev":"/task/imitation-learning","next":"/task/imitation-learning/papers/3","papers":[{"url":"/paper/optimal-power-flow-using-graph-neural","slug":"optimal-power-flow-using-graph-neural","title":"Optimal Power Flow Using Graph Neural Networks","date":"2019-10-21","arxiv_id":"1910.09658","repositories_listed":2,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/optimal-power-flow-using-graph-neural#ran","syntology_url":"https://syntology.ai/paper/1910.09658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09658"}},"official":null}},{"url":"/paper/learning-calibratable-policies-using","slug":"learning-calibratable-policies-using","title":"Learning Calibratable Policies using Programmatic Style-Consistency","date":"2019-10-02","arxiv_id":"1910.01179","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-calibratable-policies-using#ran","syntology_url":"https://syntology.ai/paper/1910.01179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01179"}},"official":{"repos":["ezhan94/calibratable-style-consistency"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/rlbench-the-robot-learning-benchmark-learning","slug":"rlbench-the-robot-learning-benchmark-learning","title":"RLBench: The Robot Learning Benchmark & Learning Environment","date":"2019-09-26","arxiv_id":"1909.12271","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/rlbench-the-robot-learning-benchmark-learning#ran","syntology_url":"https://syntology.ai/paper/1909.12271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.12271"}},"official":{"repos":["stepjam/RLBench"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/learning-controls-using-cross-modal","slug":"learning-controls-using-cross-modal","title":"Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations","date":"2019-09-16","arxiv_id":"1909.06993","repositories_listed":2,"syntology":null},{"url":"/paper/ranking-based-reward-extrapolation-without","slug":"ranking-based-reward-extrapolation-without","title":"Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations","date":"2019-07-09","arxiv_id":"1907.03976","repositories_listed":2,"syntology":null},{"url":"/paper/supervise-thyself-examining-self-supervised","slug":"supervise-thyself-examining-self-supervised","title":"Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments","date":"2019-06-27","arxiv_id":"1906.11951","repositories_listed":2,"syntology":null},{"url":"/paper/moet-interpretable-and-verifiable","slug":"moet-interpretable-and-verifiable","title":"MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning","date":"2019-06-16","arxiv_id":"1906.06717","repositories_listed":2,"syntology":null},{"url":"/paper/190600535","slug":"190600535","title":"Towards Interactive Training of Non-Player Characters in Video Games","date":"2019-06-03","arxiv_id":"1906.00535","repositories_listed":2,"syntology":null},{"url":"/paper/causal-confusion-in-imitation-learning","slug":"causal-confusion-in-imitation-learning","title":"Causal Confusion in Imitation Learning","date":"2019-05-28","arxiv_id":"1905.11979","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/causal-confusion-in-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1905.11979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11979"}},"official":null}},{"url":"/paper/random-expert-distillation-imitation-learning","slug":"random-expert-distillation-imitation-learning","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","date":"2019-05-16","arxiv_id":"1905.06750","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/random-expert-distillation-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1905.06750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.06750"}},"official":{"repos":["RuohanW/RED"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-the-limitations-of-behavior-cloning","slug":"exploring-the-limitations-of-behavior-cloning","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","date":"2019-04-18","arxiv_id":"1904.08980","repositories_listed":2,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 4 unverified","sample_list":"/paper/exploring-the-limitations-of-behavior-cloning#ran","syntology_url":"https://syntology.ai/paper/1904.08980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08980"}},"official":{"repos":["felipecode/coiltraine"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-exploration-policies-for-navigation","slug":"learning-exploration-policies-for-navigation","title":"Learning Exploration Policies for Navigation","date":"2019-03-05","arxiv_id":"1903.01959","repositories_listed":2,"syntology":null},{"url":"/paper/reward-learning-from-human-preferences-and","slug":"reward-learning-from-human-preferences-and","title":"Reward learning from human preferences and demonstrations in Atari","date":"2018-11-15","arxiv_id":"1811.06521","repositories_listed":2,"syntology":null},{"url":"/paper/differentiable-mpc-for-end-to-end-planning","slug":"differentiable-mpc-for-end-to-end-planning","title":"Differentiable MPC for End-to-end Planning and Control","date":"2018-10-31","arxiv_id":"1810.13400","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/differentiable-mpc-for-end-to-end-planning#ran","syntology_url":"https://syntology.ai/paper/1810.13400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.13400"}},"official":{"repos":["locuslab/differentiable-mpc"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/neural-modular-control-for-embodied-question","slug":"neural-modular-control-for-embodied-question","title":"Neural Modular Control for Embodied Question Answering","date":"2018-10-26","arxiv_id":"1810.11181","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"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) · 5 unverified","sample_list":"/paper/neural-modular-control-for-embodied-question#ran","syntology_url":"https://syntology.ai/paper/1810.11181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11181"}},"official":null}},{"url":"/paper/virtual-taobao-virtualizing-real-world-online","slug":"virtual-taobao-virtualizing-real-world-online","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","date":"2018-05-25","arxiv_id":"1805.10000","repositories_listed":2,"syntology":null},{"url":"/paper/verifiable-reinforcement-learning-via-policy","slug":"verifiable-reinforcement-learning-via-policy","title":"Verifiable Reinforcement Learning via Policy Extraction","date":"2018-05-22","arxiv_id":"1805.08328","repositories_listed":2,"syntology":null},{"url":"/paper/imitating-latent-policies-from-observation","slug":"imitating-latent-policies-from-observation","title":"Imitating Latent Policies from Observation","date":"2018-05-21","arxiv_id":"1805.07914","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/imitating-latent-policies-from-observation#ran","syntology_url":"https://syntology.ai/paper/1805.07914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07914"}},"official":{"repos":["ashedwards/ILPO"],"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/generating-multi-agent-trajectories-using","slug":"generating-multi-agent-trajectories-using","title":"Generating Multi-Agent Trajectories using Programmatic Weak Supervision","date":"2018-03-20","arxiv_id":"1803.07612","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generating-multi-agent-trajectories-using#ran","syntology_url":"https://syntology.ai/paper/1803.07612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07612"}},"official":{"repos":["ezhan94/gen-MA-BC","ezhan94/multiagent-programmatic-supervision"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/codraw-collaborative-drawing-as-a-testbed-for","slug":"codraw-collaborative-drawing-as-a-testbed-for","title":"CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication","date":"2017-12-15","arxiv_id":"1712.05558","repositories_listed":2,"syntology":null},{"url":"/paper/ai2-thor-an-interactive-3d-environment-for","slug":"ai2-thor-an-interactive-3d-environment-for","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","date":"2017-12-14","arxiv_id":"1712.05474","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai2-thor-an-interactive-3d-environment-for#ran","syntology_url":"https://syntology.ai/paper/1712.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05474"}},"official":{"repos":["allenai/ai2thor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-atari-grand-challenge-dataset","slug":"the-atari-grand-challenge-dataset","title":"The Atari Grand Challenge Dataset","date":"2017-05-31","arxiv_id":"1705.10998","repositories_listed":2,"syntology":null},{"url":"/paper/dart-noise-injection-for-robust-imitation","slug":"dart-noise-injection-for-robust-imitation","title":"DART: Noise Injection for Robust Imitation Learning","date":"2017-03-27","arxiv_id":"1703.09327","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dart-noise-injection-for-robust-imitation#ran","syntology_url":"https://syntology.ai/paper/1703.09327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09327"}},"official":{"repos":["BerkeleyAutomation/DART"],"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/smooth-imitation-learning-for-online-sequence","slug":"smooth-imitation-learning-for-online-sequence","title":"Smooth Imitation Learning for Online Sequence Prediction","date":"2016-06-03","arxiv_id":"1606.00968","repositories_listed":2,"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/smooth-imitation-learning-for-online-sequence#ran","syntology_url":"https://syntology.ai/paper/1606.00968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.00968"}},"official":{"repos":["hoangminhle/SIMILE"],"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/advancing-learnable-multi-agent-pathfinding","slug":"advancing-learnable-multi-agent-pathfinding","title":"Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning","date":"2025-06-30","arxiv_id":"2506.23793","repositories_listed":1,"syntology":null},{"url":"/paper/robot-gated-interactive-imitation-learning","slug":"robot-gated-interactive-imitation-learning","title":"Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism","date":"2025-06-10","arxiv_id":"2506.09176","repositories_listed":1,"syntology":null},{"url":"/paper/solving-the-job-shop-scheduling-problem-with-1","slug":"solving-the-job-shop-scheduling-problem-with-1","title":"Solving the Job Shop Scheduling Problem with Graph Neural Networks: A Customizable Reinforcement Learning Environment","date":"2025-06-10","arxiv_id":"2506.13781","repositories_listed":1,"syntology":null},{"url":"/paper/a-smooth-sea-never-made-a-skilled-texttt","slug":"a-smooth-sea-never-made-a-skilled-texttt","title":"A Smooth Sea Never Made a Skilled $\\texttt{SAILOR}$: Robust Imitation via Learning to Search","date":"2025-06-05","arxiv_id":"2506.05294","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-tool-augmented-large-language-1","slug":"advancing-tool-augmented-large-language-1","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning","date":"2025-06-05","arxiv_id":"2506.04625","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-guided-human-ai-collaboration","slug":"confidence-guided-human-ai-collaboration","title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","date":"2025-06-04","arxiv_id":"2506.03568","repositories_listed":1,"syntology":null},{"url":"/paper/normalizing-flows-are-capable-models-for-rl","slug":"normalizing-flows-are-capable-models-for-rl","title":"Normalizing Flows are Capable Models for RL","date":"2025-05-29","arxiv_id":"2505.23527","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-action-model-with-open-world","slug":"vision-language-action-model-with-open-world","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","date":"2025-05-28","arxiv_id":"2505.21906","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vision-language-action-model-with-open-world#ran","syntology_url":"https://syntology.ai/paper/2505.21906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21906"}},"official":null}},{"url":"/paper/inverse-q-learning-done-right-offline","slug":"inverse-q-learning-done-right-offline","title":"Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^π$-Realizable MDPs","date":"2025-05-26","arxiv_id":"2505.19946","repositories_listed":1,"syntology":null},{"url":"/paper/reasonplan-unified-scene-prediction-and","slug":"reasonplan-unified-scene-prediction-and","title":"ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving","date":"2025-05-26","arxiv_id":"2505.20024","repositories_listed":1,"syntology":null},{"url":"/paper/structured-reinforcement-learning-for-1","slug":"structured-reinforcement-learning-for-1","title":"Structured Reinforcement Learning for Combinatorial Decision-Making","date":"2025-05-25","arxiv_id":"2505.19053","repositories_listed":1,"syntology":null},{"url":"/paper/guided-policy-optimization-under-partial","slug":"guided-policy-optimization-under-partial","title":"Guided Policy Optimization under Partial Observability","date":"2025-05-21","arxiv_id":"2505.15418","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/guided-policy-optimization-under-partial#ran","syntology_url":"https://syntology.ai/paper/2505.15418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15418"}},"official":{"repos":["liyheng/GPO"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/guiding-data-collection-via-factored-scaling","slug":"guiding-data-collection-via-factored-scaling","title":"Guiding Data Collection via Factored Scaling Curves","date":"2025-05-12","arxiv_id":"2505.07728","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-for-autonomous-driving","slug":"imitation-learning-for-autonomous-driving","title":"Imitation Learning for Autonomous Driving: Insights from Real-World Testing","date":"2025-04-26","arxiv_id":"2504.18847","repositories_listed":1,"syntology":null},{"url":"/paper/carl-learning-scalable-planning-policies-with","slug":"carl-learning-scalable-planning-policies-with","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","date":"2025-04-24","arxiv_id":"2504.17838","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/carl-learning-scalable-planning-policies-with#ran","syntology_url":"https://syntology.ai/paper/2504.17838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.17838"}},"official":{"repos":["autonomousvision/CaRL"],"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/improving-in-context-learning-with-reasoning","slug":"improving-in-context-learning-with-reasoning","title":"Improving In-Context Learning with Reasoning Distillation","date":"2025-04-14","arxiv_id":"2504.10647","repositories_listed":1,"syntology":null},{"url":"/paper/prior-does-matter-visual-navigation-via","slug":"prior-does-matter-visual-navigation-via","title":"Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models","date":"2025-04-14","arxiv_id":"2504.10041","repositories_listed":1,"syntology":null},{"url":"/paper/toward-aligning-human-and-robot-actions-via","slug":"toward-aligning-human-and-robot-actions-via","title":"Toward Aligning Human and Robot Actions via Multi-Modal Demonstration Learning","date":"2025-04-14","arxiv_id":"2504.11493","repositories_listed":1,"syntology":null},{"url":"/paper/assistancezero-scalably-solving-assistance","slug":"assistancezero-scalably-solving-assistance","title":"AssistanceZero: Scalably Solving Assistance Games","date":"2025-04-09","arxiv_id":"2504.07091","repositories_listed":1,"syntology":null},{"url":"/paper/cafe-ad-cross-scenario-adaptive-feature","slug":"cafe-ad-cross-scenario-adaptive-feature","title":"CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving","date":"2025-04-09","arxiv_id":"2504.06584","repositories_listed":1,"syntology":null},{"url":"/paper/zeromimic-distilling-robotic-manipulation","slug":"zeromimic-distilling-robotic-manipulation","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","date":"2025-03-31","arxiv_id":"2503.23877","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-reasoner-synergizing-visual-search","slug":"embodied-reasoner-synergizing-visual-search","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","date":"2025-03-27","arxiv_id":"2503.21696","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-sketch-guided-path-planning","slug":"end-to-end-sketch-guided-path-planning","title":"End-to-end Sketch-Guided Path Planning through Imitation Learning for Autonomous Mobile Robots","date":"2025-03-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/denoising-based-contractive-imitation","slug":"denoising-based-contractive-imitation","title":"Denoising-based Contractive Imitation Learning","date":"2025-03-20","arxiv_id":"2503.15918","repositories_listed":1,"syntology":null},{"url":"/paper/had-gen-human-like-and-diverse-driving","slug":"had-gen-human-like-and-diverse-driving","title":"HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generation","date":"2025-03-19","arxiv_id":"2503.15049","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-free-autoregressive-action","slug":"quantization-free-autoregressive-action","title":"Quantization-Free Autoregressive Action Transformer","date":"2025-03-18","arxiv_id":"2503.14259","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-detect-failures-without-failure-data","slug":"can-we-detect-failures-without-failure-data","title":"Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies","date":"2025-03-11","arxiv_id":"2503.08558","repositories_listed":1,"syntology":null},{"url":"/paper/v-max-making-rl-practical-for-autonomous","slug":"v-max-making-rl-practical-for-autonomous","title":"V-Max: A Reinforcement Learning Framework for Autonomous Driving","date":"2025-03-11","arxiv_id":"2503.08388","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-approach-to-constraint-aware","slug":"a-simple-approach-to-constraint-aware","title":"A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing","date":"2025-03-10","arxiv_id":"2503.07737","repositories_listed":1,"syntology":null},{"url":"/paper/pointvla-injecting-the-3d-world-into-vision","slug":"pointvla-injecting-the-3d-world-into-vision","title":"PointVLA: Injecting the 3D World into Vision-Language-Action Models","date":"2025-03-10","arxiv_id":"2503.07511","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pointvla-injecting-the-3d-world-into-vision#ran","syntology_url":"https://syntology.ai/paper/2503.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07511"}},"official":null}},{"url":"/paper/on-a-connection-between-imitation-learning","slug":"on-a-connection-between-imitation-learning","title":"On a Connection Between Imitation Learning and RLHF","date":"2025-03-07","arxiv_id":"2503.05079","repositories_listed":1,"syntology":null},{"url":"/paper/reactive-diffusion-policy-slow-fast-visual","slug":"reactive-diffusion-policy-slow-fast-visual","title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation","date":"2025-03-04","arxiv_id":"2503.02881","repositories_listed":1,"syntology":null},{"url":"/paper/popgym-arcade-parallel-pixelated-pomdps","slug":"popgym-arcade-parallel-pixelated-pomdps","title":"POPGym Arcade: Parallel Pixelated POMDPs","date":"2025-03-03","arxiv_id":"2503.01450","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/popgym-arcade-parallel-pixelated-pomdps#ran","syntology_url":"https://syntology.ai/paper/2503.01450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01450"}},"official":{"repos":["bolt-research/popgym_arcade"],"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/caril-confidence-aware-regression-in","slug":"caril-confidence-aware-regression-in","title":"CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous Driving","date":"2025-03-02","arxiv_id":"2503.00783","repositories_listed":1,"syntology":null},{"url":"/paper/prodapt-proprioceptive-adaptation-using-long","slug":"prodapt-proprioceptive-adaptation-using-long","title":"ProDapt: Proprioceptive Adaptation using Long-term Memory Diffusion","date":"2025-02-28","arxiv_id":"2503.00193","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-vision-language-action-models","slug":"fine-tuning-vision-language-action-models","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","date":"2025-02-27","arxiv_id":"2502.19645","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/fine-tuning-vision-language-action-models#ran","syntology_url":"https://syntology.ai/paper/2502.19645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19645"}},"official":null}},{"url":"/paper/rize-regularized-imitation-learning-via","slug":"rize-regularized-imitation-learning-via","title":"RIZE: Regularized Imitation Learning via Distributional Reinforcement Learning","date":"2025-02-27","arxiv_id":"2502.20089","repositories_listed":1,"syntology":null},{"url":"/paper/god-model-privacy-preserved-ai-school-for","slug":"god-model-privacy-preserved-ai-school-for","title":"GOD model: Privacy Preserved AI School for Personal Assistant","date":"2025-02-24","arxiv_id":"2502.18527","repositories_listed":1,"syntology":null},{"url":"/paper/vavim-and-vavam-autonomous-driving-through","slug":"vavim-and-vavam-autonomous-driving-through","title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling","date":"2025-02-21","arxiv_id":"2502.15672","repositories_listed":1,"syntology":null},{"url":"/paper/making-universal-policies-universal","slug":"making-universal-policies-universal","title":"Making Universal Policies Universal","date":"2025-02-20","arxiv_id":"2502.14777","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-reinforcement-learning-action","slug":"integrating-reinforcement-learning-action","title":"Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks","date":"2025-02-18","arxiv_id":"2502.13006","repositories_listed":1,"syntology":null},{"url":"/paper/score-based-diffusion-policy-compatible-with","slug":"score-based-diffusion-policy-compatible-with","title":"Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport","date":"2025-02-18","arxiv_id":"2502.12631","repositories_listed":1,"syntology":null},{"url":"/paper/x-il-exploring-the-design-space-of-imitation","slug":"x-il-exploring-the-design-space-of-imitation","title":"X-IL: Exploring the Design Space of Imitation Learning Policies","date":"2025-02-17","arxiv_id":"2502.12330","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/x-il-exploring-the-design-space-of-imitation#ran","syntology_url":"https://syntology.ai/paper/2502.12330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12330"}},"official":{"repos":["ALRhub/X_IL"],"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/dextrack-towards-generalizable-neural","slug":"dextrack-towards-generalizable-neural","title":"DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References","date":"2025-02-13","arxiv_id":"2502.09614","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-from-a-single-temporally","slug":"imitation-learning-from-a-single-temporally","title":"Imitation Learning from a Single Temporally Misaligned Video","date":"2025-02-08","arxiv_id":"2502.05397","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imitation-learning-from-a-single-temporally#ran","syntology_url":"https://syntology.ai/paper/2502.05397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05397"}},"official":{"repos":["portal-cornell/orca"],"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/provable-ordering-and-continuity-in-vision","slug":"provable-ordering-and-continuity-in-vision","title":"Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents","date":"2025-02-03","arxiv_id":"2502.01218","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/provable-ordering-and-continuity-in-vision#ran","syntology_url":"https://syntology.ai/paper/2502.01218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01218"}},"official":{"repos":["daisy-zzz/actol"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vilp-imitation-learning-with-latent-video","slug":"vilp-imitation-learning-with-latent-video","title":"VILP: Imitation Learning with Latent Video Planning","date":"2025-02-03","arxiv_id":"2502.01784","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-planning-for-autonomous","slug":"diffusion-based-planning-for-autonomous","title":"Diffusion-Based Planning for Autonomous Driving with Flexible Guidance","date":"2025-01-26","arxiv_id":"2501.15564","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/diffusion-based-planning-for-autonomous#ran","syntology_url":"https://syntology.ai/paper/2501.15564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15564"}},"official":null}},{"url":"/paper/advancing-language-model-reasoning-through","slug":"advancing-language-model-reasoning-through","title":"Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling","date":"2025-01-20","arxiv_id":"2501.11651","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-online-reinforcement-learning-with","slug":"enhancing-online-reinforcement-learning-with","title":"Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data","date":"2025-01-13","arxiv_id":"2501.07346","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-graph-neural-networks-for","slug":"generalizable-graph-neural-networks-for","title":"Generalizable Graph Neural Networks for Robust Power Grid Topology Control","date":"2025-01-13","arxiv_id":"2501.07186","repositories_listed":1,"syntology":null},{"url":"/paper/learning-flexible-heterogeneous-coordination","slug":"learning-flexible-heterogeneous-coordination","title":"Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination","date":"2025-01-10","arxiv_id":"2501.06058","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/learning-flexible-heterogeneous-coordination#ran","syntology_url":"https://syntology.ai/paper/2501.06058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06058"}},"official":{"repos":["kfu02/jaxmarl"],"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/smart-imitator-learning-from-imperfect","slug":"smart-imitator-learning-from-imperfect","title":"Smart Imitator: Learning from Imperfect Clinical Decisions","date":"2025-01-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-from-suboptimal","slug":"imitation-learning-from-suboptimal","title":"Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker","date":"2024-12-28","arxiv_id":"2412.20193","repositories_listed":1,"syntology":null},{"url":"/paper/decoding-fairness-a-reinforcement-learning","slug":"decoding-fairness-a-reinforcement-learning","title":"Decoding fairness: a reinforcement learning perspective","date":"2024-12-20","arxiv_id":"2412.16249","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-diffusion-transformer-policies-with","slug":"efficient-diffusion-transformer-policies-with","title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","date":"2024-12-17","arxiv_id":"2412.12953","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-diffusion-transformer-policies-with#ran","syntology_url":"https://syntology.ai/paper/2412.12953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12953"}},"official":null}},{"url":"/paper/contractive-dynamical-imitation-policies-for","slug":"contractive-dynamical-imitation-policies-for","title":"Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery","date":"2024-12-10","arxiv_id":"2412.07544","repositories_listed":1,"syntology":null},{"url":"/paper/meta-controller-few-shot-imitation-of-unseen","slug":"meta-controller-few-shot-imitation-of-unseen","title":"Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control","date":"2024-12-10","arxiv_id":"2412.12147","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-controller-few-shot-imitation-of-unseen#ran","syntology_url":"https://syntology.ai/paper/2412.12147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12147"}},"official":{"repos":["seongwoongcho/meta-controller"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/maniskill-hab-a-benchmark-for-low-level","slug":"maniskill-hab-a-benchmark-for-low-level","title":"ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks","date":"2024-12-09","arxiv_id":"2412.13211","repositories_listed":1,"syntology":null},{"url":"/paper/demo-reframing-dialogue-interaction-with-fine","slug":"demo-reframing-dialogue-interaction-with-fine","title":"DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling","date":"2024-12-06","arxiv_id":"2412.04905","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/demo-reframing-dialogue-interaction-with-fine#ran","syntology_url":"https://syntology.ai/paper/2412.04905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04905"}},"official":{"repos":["mozerwang/demo"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/teamcraft-a-benchmark-for-multi-modal-multi","slug":"teamcraft-a-benchmark-for-multi-modal-multi","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","date":"2024-12-06","arxiv_id":"2412.05255","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/teamcraft-a-benchmark-for-multi-modal-multi#ran","syntology_url":"https://syntology.ai/paper/2412.05255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05255"}},"official":{"repos":["teamcraft-bench/teamcraft"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/befl-balancing-energy-consumption-in","slug":"befl-balancing-energy-consumption-in","title":"BEFL: Balancing Energy Consumption in Federated Learning for Mobile Edge IoT","date":"2024-12-05","arxiv_id":"2412.03950","repositories_listed":1,"syntology":null},{"url":"/paper/learning-speed-adaptive-walking-agent-using","slug":"learning-speed-adaptive-walking-agent-using","title":"Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation","date":"2024-12-05","arxiv_id":"2412.03949","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-speed-adaptive-walking-agent-using#ran","syntology_url":"https://syntology.ai/paper/2412.03949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03949"}},"official":{"repos":["MetaMobilityLabCMU/speed-adaptive-agent"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-on-one-mode-addressing-multi","slug":"learning-on-one-mode-addressing-multi","title":"Learning on One Mode: Addressing Multi-Modality in Offline Reinforcement Learning","date":"2024-12-04","arxiv_id":"2412.03258","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-on-one-mode-addressing-multi#ran","syntology_url":"https://syntology.ai/paper/2412.03258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03258"}},"official":{"repos":["MianchuWang/LOM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/global-tensor-motion-planning","slug":"global-tensor-motion-planning","title":"Global Tensor Motion Planning","date":"2024-11-28","arxiv_id":"2411.19393","repositories_listed":1,"syntology":null},{"url":"/paper/g3flow-generative-3d-semantic-flow-for-pose","slug":"g3flow-generative-3d-semantic-flow-for-pose","title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation","date":"2024-11-27","arxiv_id":"2411.18369","repositories_listed":1,"syntology":null},{"url":"/paper/learning-for-long-horizon-planning-via-neuro","slug":"learning-for-long-horizon-planning-via-neuro","title":"Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation","date":"2024-11-27","arxiv_id":"2411.18201","repositories_listed":1,"syntology":null},{"url":"/paper/citywalker-learning-embodied-urban-navigation","slug":"citywalker-learning-embodied-urban-navigation","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","date":"2024-11-26","arxiv_id":"2411.17820","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/citywalker-learning-embodied-urban-navigation#ran","syntology_url":"https://syntology.ai/paper/2411.17820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17820"}},"official":{"repos":["ai4ce/CityWalker"],"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/neuromorphic-attitude-estimation-and-control","slug":"neuromorphic-attitude-estimation-and-control","title":"Neuromorphic Attitude Estimation and Control","date":"2024-11-21","arxiv_id":"2411.13945","repositories_listed":1,"syntology":null},{"url":"/paper/learning-generalizable-3d-manipulation-with","slug":"learning-generalizable-3d-manipulation-with","title":"Learning Generalizable 3D Manipulation With 10 Demonstrations","date":"2024-11-15","arxiv_id":"2411.10203","repositories_listed":1,"syntology":null},{"url":"/paper/off-dynamics-reinforcement-learning-via","slug":"off-dynamics-reinforcement-learning-via","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","date":"2024-11-15","arxiv_id":"2411.09891","repositories_listed":1,"syntology":null},{"url":"/paper/learning-memory-mechanisms-for-decision","slug":"learning-memory-mechanisms-for-decision","title":"Learning Memory Mechanisms for Decision Making through Demonstrations","date":"2024-11-12","arxiv_id":"2411.07954","repositories_listed":1,"syntology":null},{"url":"/paper/igdrivsim-a-benchmark-for-the-imitation-gap","slug":"igdrivsim-a-benchmark-for-the-imitation-gap","title":"IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving","date":"2024-11-07","arxiv_id":"2411.04653","repositories_listed":1,"syntology":null},{"url":"/paper/stem-ob-generalizable-visual-imitation","slug":"stem-ob-generalizable-visual-imitation","title":"Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion","date":"2024-11-07","arxiv_id":"2411.04919","repositories_listed":1,"syntology":null},{"url":"/paper/garmentlab-a-unified-simulation-and-benchmark","slug":"garmentlab-a-unified-simulation-and-benchmark","title":"GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation","date":"2024-11-02","arxiv_id":"2411.01200","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/garmentlab-a-unified-simulation-and-benchmark#ran","syntology_url":"https://syntology.ai/paper/2411.01200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01200"}},"official":{"repos":["GarmentLab/GarmentLab"],"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/egomimic-scaling-imitation-learning-via","slug":"egomimic-scaling-imitation-learning-via","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","date":"2024-10-31","arxiv_id":"2410.24221","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/egomimic-scaling-imitation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2410.24221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24221"}},"official":{"repos":["SimarKareer/EgoMimic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"9fa3544fea98c1ec47c5eb2905e190d3dfb71a1f13cf85fa1ebda0598a003012","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}