{"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/ran/1","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":"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":3,"rows_per_page":100,"rows":[1,100],"of":234,"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/papers/ran/1","prev":null,"next":"/task/imitation-learning/papers/ran/2","papers":[{"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/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/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/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/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/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/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/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/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/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/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/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/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/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"]}}},{"url":"/paper/openwebvoyager-building-multimodal-web-agents","slug":"openwebvoyager-building-multimodal-web-agents","title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","date":"2024-10-25","arxiv_id":"2410.19609","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/openwebvoyager-building-multimodal-web-agents#ran","syntology_url":"https://syntology.ai/paper/2410.19609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19609"}},"official":{"repos":["minorjerry/openwebvoyager"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusing-states-and-matching-scores-a-new","slug":"diffusing-states-and-matching-scores-a-new","title":"Diffusing States and Matching Scores: A New Framework for Imitation Learning","date":"2024-10-17","arxiv_id":"2410.13855","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"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 2 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/diffusing-states-and-matching-scores-a-new#ran","syntology_url":"https://syntology.ai/paper/2410.13855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13855"}},"official":{"repos":["ziqian2000/smiling"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-leverage-demonstration-data-in","slug":"how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","arxiv_id":"2410.10093","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":10,"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/how-to-leverage-demonstration-data-in#ran","syntology_url":"https://syntology.ai/paper/2410.10093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10093"}},"official":{"repos":["tengxiao1/gsil"],"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/zero-shot-offline-imitation-learning-via","slug":"zero-shot-offline-imitation-learning-via","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","date":"2024-10-11","arxiv_id":"2410.08751","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/zero-shot-offline-imitation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2410.08751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08751"}},"official":{"repos":["martius-lab/zilot"],"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/divscene-benchmarking-lvlms-for-object","slug":"divscene-benchmarking-lvlms-for-object","title":"DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects","date":"2024-10-03","arxiv_id":"2410.02730","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/divscene-benchmarking-lvlms-for-object#ran","syntology_url":"https://syntology.ai/paper/2410.02730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02730"}},"official":{"repos":["zhaowei-wang-nlp/divscene"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/relic-a-recipe-for-64k-steps-of-in-context","slug":"relic-a-recipe-for-64k-steps-of-in-context","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","date":"2024-10-03","arxiv_id":"2410.02751","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":7,"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/relic-a-recipe-for-64k-steps-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2410.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02751"}},"official":{"repos":["aielawady/relic"],"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/maniskill3-gpu-parallelized-robotics","slug":"maniskill3-gpu-parallelized-robotics","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","date":"2024-10-01","arxiv_id":"2410.00425","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/maniskill3-gpu-parallelized-robotics#ran","syntology_url":"https://syntology.ai/paper/2410.00425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00425"}},"official":{"repos":["haosulab/ManiSkill"],"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/flowretrieval-flow-guided-data-retrieval-for","slug":"flowretrieval-flow-guided-data-retrieval-for","title":"FlowRetrieval: Flow-Guided Data Retrieval for Few-Shot Imitation Learning","date":"2024-08-29","arxiv_id":"2408.16944","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/flowretrieval-flow-guided-data-retrieval-for#ran","syntology_url":"https://syntology.ai/paper/2408.16944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16944"}},"official":null}},{"url":"/paper/mapf-gpt-imitation-learning-for-multi-agent-1","slug":"mapf-gpt-imitation-learning-for-multi-agent-1","title":"MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale","date":"2024-08-29","arxiv_id":"2409.00134","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/mapf-gpt-imitation-learning-for-multi-agent-1#ran","syntology_url":"https://syntology.ai/paper/2409.00134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00134"}},"official":{"repos":["cognitiveaisystems/mapf-gpt"],"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/in-context-imitation-learning-via-next-token","slug":"in-context-imitation-learning-via-next-token","title":"In-Context Imitation Learning via Next-Token Prediction","date":"2024-08-28","arxiv_id":"2408.15980","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-context-imitation-learning-via-next-token#ran","syntology_url":"https://syntology.ai/paper/2408.15980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15980"}},"official":{"repos":["Max-Fu/icrt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/explorative-imitation-learning-a-path","slug":"explorative-imitation-learning-a-path","title":"Explorative Imitation Learning: A Path Signature Approach for Continuous Environments","date":"2024-07-05","arxiv_id":"2407.04856","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explorative-imitation-learning-a-path#ran","syntology_url":"https://syntology.ai/paper/2407.04856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04856"}},"official":{"repos":["NathanGavenski/CILO"],"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","unlocated"]}}},{"url":"/paper/equivariant-diffusion-policy","slug":"equivariant-diffusion-policy","title":"Equivariant Diffusion Policy","date":"2024-07-01","arxiv_id":"2407.01812","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/equivariant-diffusion-policy#ran","syntology_url":"https://syntology.ai/paper/2407.01812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01812"}},"official":{"repos":["pointW/equidiff"],"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/iterative-sizing-field-prediction-for","slug":"iterative-sizing-field-prediction-for","title":"Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations","date":"2024-06-20","arxiv_id":"2406.14161","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/iterative-sizing-field-prediction-for#ran","syntology_url":"https://syntology.ai/paper/2406.14161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14161"}},"official":{"repos":["NiklasFreymuth/AMBER"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evil-evolution-strategies-for-generalisable","slug":"evil-evolution-strategies-for-generalisable","title":"EvIL: Evolution Strategies for Generalisable Imitation Learning","date":"2024-06-15","arxiv_id":"2406.11905","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evil-evolution-strategies-for-generalisable#ran","syntology_url":"https://syntology.ai/paper/2406.11905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11905"}},"official":{"repos":["SilviaSapora/evil"],"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/openvla-an-open-source-vision-language-action","slug":"openvla-an-open-source-vision-language-action","title":"OpenVLA: An Open-Source Vision-Language-Action Model","date":"2024-06-13","arxiv_id":"2406.09246","repositories_listed":3,"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/openvla-an-open-source-vision-language-action#ran","syntology_url":"https://syntology.ai/paper/2406.09246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09246"}},"official":null}},{"url":"/paper/is-value-learning-really-the-main-bottleneck","slug":"is-value-learning-really-the-main-bottleneck","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","date":"2024-06-13","arxiv_id":"2406.09329","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 6 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/is-value-learning-really-the-main-bottleneck#ran","syntology_url":"https://syntology.ai/paper/2406.09329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09329"}},"official":null}},{"url":"/paper/mail-improving-imitation-learning-with-mamba","slug":"mail-improving-imitation-learning-with-mamba","title":"MaIL: Improving Imitation Learning with Mamba","date":"2024-06-12","arxiv_id":"2406.08234","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mail-improving-imitation-learning-with-mamba#ran","syntology_url":"https://syntology.ai/paper/2406.08234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08234"}},"official":{"repos":["alrhub/mail"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tedi-policy-temporally-entangled-diffusion","slug":"tedi-policy-temporally-entangled-diffusion","title":"Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models","date":"2024-06-07","arxiv_id":"2406.04806","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":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tedi-policy-temporally-entangled-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.04806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04806"}},"official":{"repos":["Streaming-Diffusion-Policy/streaming_diffusion_policy"],"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/how-to-leverage-diverse-demonstrations-in","slug":"how-to-leverage-diverse-demonstrations-in","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","date":"2024-05-24","arxiv_id":"2405.17476","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"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) · 5 unverified","sample_list":"/paper/how-to-leverage-diverse-demonstrations-in#ran","syntology_url":"https://syntology.ai/paper/2405.17476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17476"}},"official":{"repos":["hansenhua/ilid-offline-imitation-learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/ollie-imitation-learning-from-offline","slug":"ollie-imitation-learning-from-offline","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","date":"2024-05-24","arxiv_id":"2405.17477","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":4,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"phrase":"8 ran (of which 4 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) · 5 unverified","sample_list":"/paper/ollie-imitation-learning-from-offline#ran","syntology_url":"https://syntology.ai/paper/2405.17477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17477"}},"official":{"repos":["hansenhua/ollie-offline-to-online-imitation-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/ag2manip-learning-novel-manipulation-skills","slug":"ag2manip-learning-novel-manipulation-skills","title":"Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations","date":"2024-04-26","arxiv_id":"2404.17521","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ag2manip-learning-novel-manipulation-skills#ran","syntology_url":"https://syntology.ai/paper/2404.17521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17521"}},"official":{"repos":["Xiaoyao-Li/Ag2Manip"],"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/juicer-data-efficient-imitation-learning-for","slug":"juicer-data-efficient-imitation-learning-for","title":"JUICER: Data-Efficient Imitation Learning for Robotic Assembly","date":"2024-04-04","arxiv_id":"2404.03729","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/juicer-data-efficient-imitation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2404.03729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03729"}},"official":{"repos":["ankile/imitation-juicer"],"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/lasil-learner-aware-supervised-imitation","slug":"lasil-learner-aware-supervised-imitation","title":"LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation","date":"2024-03-26","arxiv_id":"2403.17601","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/lasil-learner-aware-supervised-imitation#ran","syntology_url":"https://syntology.ai/paper/2403.17601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17601"}},"official":{"repos":["kguo-cs/lsail"],"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/self-improvement-for-neural-combinatorial","slug":"self-improvement-for-neural-combinatorial","title":"Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement","date":"2024-03-22","arxiv_id":"2403.15180","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/self-improvement-for-neural-combinatorial#ran","syntology_url":"https://syntology.ai/paper/2403.15180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15180"}},"official":{"repos":["grimmlab/gumbeldore"],"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/3d-diffusion-policy","slug":"3d-diffusion-policy","title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","date":"2024-03-06","arxiv_id":"2403.03954","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3d-diffusion-policy#ran","syntology_url":"https://syntology.ai/paper/2403.03954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03954"}},"official":{"repos":["YanjieZe/3D-Diffusion-Policy"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/behavior-generation-with-latent-actions","slug":"behavior-generation-with-latent-actions","title":"Behavior Generation with Latent Actions","date":"2024-03-05","arxiv_id":"2403.03181","repositories_listed":2,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/behavior-generation-with-latent-actions#ran","syntology_url":"https://syntology.ai/paper/2403.03181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03181"}},"official":{"repos":["jayLEE0301/vq_bet_official"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/imitation-learning-datasets-a-toolkit-for","slug":"imitation-learning-datasets-a-toolkit-for","title":"Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking","date":"2024-03-01","arxiv_id":"2403.00550","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-datasets-a-toolkit-for#ran","syntology_url":"https://syntology.ai/paper/2403.00550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00550"}},"official":{"repos":["nathangavenski/il-datasets"],"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/behavioral-refinement-via-interpolant-based","slug":"behavioral-refinement-via-interpolant-based","title":"Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion","date":"2024-02-25","arxiv_id":"2402.16075","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/behavioral-refinement-via-interpolant-based#ran","syntology_url":"https://syntology.ai/paper/2402.16075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16075"}},"official":{"repos":["clear-nus/bridger"],"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/himap-learning-heuristics-informed-policies","slug":"himap-learning-heuristics-informed-policies","title":"HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding","date":"2024-02-23","arxiv_id":"2402.15546","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/himap-learning-heuristics-informed-policies#ran","syntology_url":"https://syntology.ai/paper/2402.15546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15546"}},"official":{"repos":["kaist-silab/himap"],"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/subiq-inverse-soft-q-learning-for-offline","slug":"subiq-inverse-soft-q-learning-for-offline","title":"SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning","date":"2024-02-20","arxiv_id":"2402.13147","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/subiq-inverse-soft-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2402.13147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13147"}},"official":{"repos":["hmhuy0/SPRINQL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prise-learning-temporal-action-abstractions","slug":"prise-learning-temporal-action-abstractions","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","date":"2024-02-16","arxiv_id":"2402.10450","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prise-learning-temporal-action-abstractions#ran","syntology_url":"https://syntology.ai/paper/2402.10450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10450"}},"official":{"repos":["frankzheng2022/prise"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-improvement-using-language-feedback","slug":"policy-improvement-using-language-feedback","title":"Policy Improvement using Language Feedback Models","date":"2024-02-12","arxiv_id":"2402.07876","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/policy-improvement-using-language-feedback#ran","syntology_url":"https://syntology.ai/paper/2402.07876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07876"}},"official":{"repos":["vzhong/language_feedback_models"],"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/premier-taco-pretraining-multitask","slug":"premier-taco-pretraining-multitask","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","date":"2024-02-09","arxiv_id":"2402.06187","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"6 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/premier-taco-pretraining-multitask#ran","syntology_url":"https://syntology.ai/paper/2402.06187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06187"}},"official":{"repos":["premiertaco/premier-taco"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/difftop-differentiable-trajectory","slug":"difftop-differentiable-trajectory","title":"DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning","date":"2024-02-08","arxiv_id":"2402.05421","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/difftop-differentiable-trajectory#ran","syntology_url":"https://syntology.ai/paper/2402.05421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05421"}},"official":{"repos":["wkwan7/difftori"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/online-cascade-learning-for-efficient","slug":"online-cascade-learning-for-efficient","title":"Online Cascade Learning for Efficient Inference over Streams","date":"2024-02-07","arxiv_id":"2402.04513","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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/online-cascade-learning-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2402.04513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04513"}},"official":{"repos":["flitternie/online_cascade_learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/seabo-a-simple-search-based-method-for","slug":"seabo-a-simple-search-based-method-for","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","date":"2024-02-06","arxiv_id":"2402.03807","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/seabo-a-simple-search-based-method-for#ran","syntology_url":"https://syntology.ai/paper/2402.03807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03807"}},"official":{"repos":["dmksjfl/seabo"],"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/odice-revealing-the-mystery-of-distribution","slug":"odice-revealing-the-mystery-of-distribution","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","date":"2024-02-01","arxiv_id":"2402.00348","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":1,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/odice-revealing-the-mystery-of-distribution#ran","syntology_url":"https://syntology.ai/paper/2402.00348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00348"}},"official":{"repos":["maoliyuan/odice-pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/expert-proximity-as-surrogate-rewards-for","slug":"expert-proximity-as-surrogate-rewards-for","title":"Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning","date":"2024-02-01","arxiv_id":"2402.01057","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/expert-proximity-as-surrogate-rewards-for#ran","syntology_url":"https://syntology.ai/paper/2402.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01057"}},"official":{"repos":["stanl1y/tdil"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/langprop-a-code-optimization-framework-using","slug":"langprop-a-code-optimization-framework-using","title":"LangProp: A code optimization framework using Large Language Models applied to driving","date":"2024-01-18","arxiv_id":"2401.10314","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/langprop-a-code-optimization-framework-using#ran","syntology_url":"https://syntology.ai/paper/2401.10314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10314"}},"official":{"repos":["shuishida/langprop"],"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/diffail-diffusion-adversarial-imitation","slug":"diffail-diffusion-adversarial-imitation","title":"DiffAIL: Diffusion Adversarial Imitation Learning","date":"2023-12-11","arxiv_id":"2312.06348","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":9,"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/diffail-diffusion-adversarial-imitation#ran","syntology_url":"https://syntology.ai/paper/2312.06348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06348"}},"official":{"repos":["ml-group-sdu/diffail"],"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/backward-learning-for-goal-conditioned","slug":"backward-learning-for-goal-conditioned","title":"Backward Learning for Goal-Conditioned Policies","date":"2023-12-08","arxiv_id":"2312.05044","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/backward-learning-for-goal-conditioned#ran","syntology_url":"https://syntology.ai/paper/2312.05044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05044"}},"official":{"repos":["hauf3n/backward-learning-for-goal-conditioned-policies"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/embodied-multi-modal-agent-trained-by-an-llm","slug":"embodied-multi-modal-agent-trained-by-an-llm","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","date":"2023-11-28","arxiv_id":"2311.16714","repositories_listed":1,"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/embodied-multi-modal-agent-trained-by-an-llm#ran","syntology_url":"https://syntology.ai/paper/2311.16714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16714"}},"official":{"repos":["stevenyangyj/emma-alfworld"],"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/beyond-imitation-leveraging-fine-grained","slug":"beyond-imitation-leveraging-fine-grained","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","date":"2023-11-07","arxiv_id":"2311.04072","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beyond-imitation-leveraging-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2311.04072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04072"}},"official":{"repos":["rucaibox/figa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kinematic-aware-prompting-for-generalizable","slug":"kinematic-aware-prompting-for-generalizable","title":"Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs","date":"2023-11-06","arxiv_id":"2311.02847","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kinematic-aware-prompting-for-generalizable#ran","syntology_url":"https://syntology.ai/paper/2311.02847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02847"}},"official":{"repos":["gewu-lab/llm_articulated_object_manipulation","xwinks/llm_articulated_object_manipulation"],"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/locomujoco-a-comprehensive-imitation-learning","slug":"locomujoco-a-comprehensive-imitation-learning","title":"LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion","date":"2023-11-04","arxiv_id":"2311.02496","repositories_listed":2,"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/locomujoco-a-comprehensive-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2311.02496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02496"}},"official":{"repos":["robfiras/loco-mujoco"],"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/invariant-causal-imitation-learning-for-1","slug":"invariant-causal-imitation-learning-for-1","title":"Invariant Causal Imitation Learning for Generalizable Policies","date":"2023-11-02","arxiv_id":"2311.01489","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":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/invariant-causal-imitation-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2311.01489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01489"}},"official":{"repos":["ioanabica/invariant-causal-imitation-learning","vanderschaarlab/mlforhealthlabpub"],"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/towards-example-based-nmt-with-multi","slug":"towards-example-based-nmt-with-multi","title":"Towards Example-Based NMT with Multi-Levenshtein Transformers","date":"2023-10-13","arxiv_id":"2310.08967","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-example-based-nmt-with-multi#ran","syntology_url":"https://syntology.ai/paper/2310.08967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08967"}},"official":{"repos":["maxwell1447/fairseq"],"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/imitation-learning-from-purified","slug":"imitation-learning-from-purified","title":"Imitation Learning from Purified Demonstrations","date":"2023-10-11","arxiv_id":"2310.07143","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imitation-learning-from-purified#ran","syntology_url":"https://syntology.ai/paper/2310.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07143"}},"official":{"repos":["yunke-wang/dp-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":["found_in_text","official"]}}},{"url":"/paper/imitation-learning-from-observation-with","slug":"imitation-learning-from-observation-with","title":"Imitation Learning from Observation with Automatic Discount Scheduling","date":"2023-10-11","arxiv_id":"2310.07433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imitation-learning-from-observation-with#ran","syntology_url":"https://syntology.ai/paper/2310.07433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07433"}},"official":null}},{"url":"/paper/reinforcement-learning-in-the-era-of-llms","slug":"reinforcement-learning-in-the-era-of-llms","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","date":"2023-10-09","arxiv_id":"2310.06147","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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-in-the-era-of-llms#ran","syntology_url":"https://syntology.ai/paper/2310.06147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06147"}},"official":null}},{"url":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"11 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}},"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-bayesian-approach-to-robust-inverse","slug":"a-bayesian-approach-to-robust-inverse","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","date":"2023-09-15","arxiv_id":"2309.08571","repositories_listed":2,"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/a-bayesian-approach-to-robust-inverse#ran","syntology_url":"https://syntology.ai/paper/2309.08571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08571"}},"official":{"repos":["ran-weii/bmirl_tf"],"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/everyone-deserves-a-reward-learning","slug":"everyone-deserves-a-reward-learning","title":"Everyone Deserves A Reward: Learning Customized Human Preferences","date":"2023-09-06","arxiv_id":"2309.03126","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/everyone-deserves-a-reward-learning#ran","syntology_url":"https://syntology.ai/paper/2309.03126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03126"}},"official":{"repos":["linear95/dsp"],"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/bridgedata-v2-a-dataset-for-robot-learning-at","slug":"bridgedata-v2-a-dataset-for-robot-learning-at","title":"BridgeData V2: A Dataset for Robot Learning at Scale","date":"2023-08-24","arxiv_id":"2308.12952","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bridgedata-v2-a-dataset-for-robot-learning-at#ran","syntology_url":"https://syntology.ai/paper/2308.12952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12952"}},"official":{"repos":["rail-berkeley/BridgeData-V2"],"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/small-object-detection-via-coarse-to-fine","slug":"small-object-detection-via-coarse-to-fine","title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","date":"2023-08-18","arxiv_id":"2308.09534","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":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/small-object-detection-via-coarse-to-fine#ran","syntology_url":"https://syntology.ai/paper/2308.09534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09534"}},"official":{"repos":["shaunyuan22/cfinet"],"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/scaling-data-generation-in-vision-and","slug":"scaling-data-generation-in-vision-and","title":"Scaling Data Generation in Vision-and-Language Navigation","date":"2023-07-28","arxiv_id":"2307.15644","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/scaling-data-generation-in-vision-and#ran","syntology_url":"https://syntology.ai/paper/2307.15644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15644"}},"official":{"repos":["wz0919/scalevln"],"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/xskill-cross-embodiment-skill-discovery","slug":"xskill-cross-embodiment-skill-discovery","title":"XSkill: Cross Embodiment Skill Discovery","date":"2023-07-19","arxiv_id":"2307.09955","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/xskill-cross-embodiment-skill-discovery#ran","syntology_url":"https://syntology.ai/paper/2307.09955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09955"}},"official":{"repos":["real-stanford/xskill"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-laws-for-imitation-learning-in","slug":"scaling-laws-for-imitation-learning-in","title":"Scaling Laws for Imitation Learning in Single-Agent Games","date":"2023-07-18","arxiv_id":"2307.09423","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-laws-for-imitation-learning-in#ran","syntology_url":"https://syntology.ai/paper/2307.09423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09423"}},"official":{"repos":["princeton-nlp/il-scaling-in-games"],"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/crossway-diffusion-improving-diffusion-based","slug":"crossway-diffusion-improving-diffusion-based","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","date":"2023-07-04","arxiv_id":"2307.01849","repositories_listed":2,"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/crossway-diffusion-improving-diffusion-based#ran","syntology_url":"https://syntology.ai/paper/2307.01849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01849"}},"official":{"repos":["lostxine/crossway_diffusion"],"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/thought-cloning-learning-to-think-while-1","slug":"thought-cloning-learning-to-think-while-1","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","date":"2023-06-01","arxiv_id":"2306.00323","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/thought-cloning-learning-to-think-while-1#ran","syntology_url":"https://syntology.ai/paper/2306.00323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00323"}},"official":{"repos":["ShengranHu/Thought-Cloning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/preference-grounded-token-level-guidance-for-1","slug":"preference-grounded-token-level-guidance-for-1","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","date":"2023-06-01","arxiv_id":"2306.00398","repositories_listed":2,"syntology":{"n":18,"n_ran":8,"n_constructed":1,"n_ran_checked":2,"n_instrument":6,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/preference-grounded-token-level-guidance-for-1#ran","syntology_url":"https://syntology.ai/paper/2306.00398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00398"}},"official":{"repos":["shentao-yang/preference_grounded_guidance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/liv-language-image-representations-and","slug":"liv-language-image-representations-and","title":"LIV: Language-Image Representations and Rewards for Robotic Control","date":"2023-06-01","arxiv_id":"2306.00958","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"10 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; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/liv-language-image-representations-and#ran","syntology_url":"https://syntology.ai/paper/2306.00958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00958"}},"official":{"repos":["penn-pal-lab/liv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-essential-for-unseen-goal","slug":"what-is-essential-for-unseen-goal","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","date":"2023-05-30","arxiv_id":"2305.18882","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/what-is-essential-for-unseen-goal#ran","syntology_url":"https://syntology.ai/paper/2305.18882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18882"}},"official":{"repos":["yangrui2015/goat"],"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/coherent-soft-imitation-learning","slug":"coherent-soft-imitation-learning","title":"Coherent Soft Imitation Learning","date":"2023-05-25","arxiv_id":"2305.16498","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/coherent-soft-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2305.16498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16498"}},"official":{"repos":["google-deepmind/csil"],"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/learn-from-mistakes-through-cooperative","slug":"learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13829","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learn-from-mistakes-through-cooperative#ran","syntology_url":"https://syntology.ai/paper/2305.13829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13829"}},"official":{"repos":["dqwang122/salam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/2305-14550#ran","syntology_url":"https://syntology.ai/paper/2305.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14550"}},"official":{"repos":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/furniturebench-reproducible-real-world","slug":"furniturebench-reproducible-real-world","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","date":"2023-05-22","arxiv_id":"2305.12821","repositories_listed":1,"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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/furniturebench-reproducible-real-world#ran","syntology_url":"https://syntology.ai/paper/2305.12821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12821"}},"official":{"repos":["clvrai/furniture-bench"],"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/a-coupled-flow-approach-to-imitation-learning","slug":"a-coupled-flow-approach-to-imitation-learning","title":"A Coupled Flow Approach to Imitation Learning","date":"2023-04-29","arxiv_id":"2305.00303","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/a-coupled-flow-approach-to-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2305.00303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00303"}},"official":{"repos":["gfreund123/cfil"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/learning-to-extrapolate-a-transductive","slug":"learning-to-extrapolate-a-transductive","title":"Learning to Extrapolate: A Transductive Approach","date":"2023-04-27","arxiv_id":"2304.14329","repositories_listed":2,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":1,"phrase":"17 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-to-extrapolate-a-transductive#ran","syntology_url":"https://syntology.ai/paper/2304.14329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.14329"}},"official":{"repos":["avivne/bilinear-transduction"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/distance-weighted-supervised-learning-for","slug":"distance-weighted-supervised-learning-for","title":"Distance Weighted Supervised Learning for Offline Interaction Data","date":"2023-04-26","arxiv_id":"2304.13774","repositories_listed":1,"syntology":{"n":27,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":13,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/distance-weighted-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2304.13774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13774"}},"official":null}},{"url":"/paper/chain-of-thought-predictive-control","slug":"chain-of-thought-predictive-control","title":"Chain-of-Thought Predictive Control","date":"2023-04-03","arxiv_id":"2304.00776","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/chain-of-thought-predictive-control#ran","syntology_url":"https://syntology.ai/paper/2304.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00776"}},"official":{"repos":["seanjia/cotpc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mahalo-unifying-offline-reinforcement","slug":"mahalo-unifying-offline-reinforcement","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","date":"2023-03-30","arxiv_id":"2303.17156","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/mahalo-unifying-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2303.17156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17156"}},"official":{"repos":["anqili/mahalo"],"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/improving-code-generation-by-training-with","slug":"improving-code-generation-by-training-with","title":"Improving Code Generation by Training with Natural Language Feedback","date":"2023-03-28","arxiv_id":"2303.16749","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/improving-code-generation-by-training-with#ran","syntology_url":"https://syntology.ai/paper/2303.16749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16749"}},"official":{"repos":["nyu-mll/ILF-for-code-generation"],"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/training-language-models-with-language","slug":"training-language-models-with-language","title":"Training Language Models with Language Feedback at Scale","date":"2023-03-28","arxiv_id":"2303.16755","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/training-language-models-with-language#ran","syntology_url":"https://syntology.ai/paper/2303.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16755"}},"official":{"repos":["jeremyalain/imitation_learning_from_language_feedback"],"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/optimal-transport-for-offline-imitation","slug":"optimal-transport-for-offline-imitation","title":"Optimal Transport for Offline Imitation Learning","date":"2023-03-24","arxiv_id":"2303.13971","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimal-transport-for-offline-imitation#ran","syntology_url":"https://syntology.ai/paper/2303.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13971"}},"official":{"repos":["ethanluoyc/optimal_transport_reward"],"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/teach-a-robot-to-fish-versatile-imitation","slug":"teach-a-robot-to-fish-versatile-imitation","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","date":"2023-03-02","arxiv_id":"2303.01497","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/teach-a-robot-to-fish-versatile-imitation#ran","syntology_url":"https://syntology.ai/paper/2303.01497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01497"}},"official":{"repos":["siddhanthaldar/FISH"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/language-driven-representation-learning-for","slug":"language-driven-representation-learning-for","title":"Language-Driven Representation Learning for Robotics","date":"2023-02-24","arxiv_id":"2302.12766","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/language-driven-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2302.12766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12766"}},"official":{"repos":["siddk/voltron-evaluation","siddk/voltron-robotics"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/k-shap-policy-clustering-algorithm-for","slug":"k-shap-policy-clustering-algorithm-for","title":"K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs","date":"2023-02-23","arxiv_id":"2302.11996","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/k-shap-policy-clustering-algorithm-for#ran","syntology_url":"https://syntology.ai/paper/2302.11996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11996"}},"official":null}},{"url":"/paper/imitation-from-arbitrary-experience-a-dual","slug":"imitation-from-arbitrary-experience-a-dual","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","date":"2023-02-16","arxiv_id":"2302.08560","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imitation-from-arbitrary-experience-a-dual#ran","syntology_url":"https://syntology.ai/paper/2302.08560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08560"}},"official":{"repos":["hari-sikchi/DVL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pretraining-language-models-with-human","slug":"pretraining-language-models-with-human","title":"Pretraining Language Models with Human Preferences","date":"2023-02-16","arxiv_id":"2302.08582","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pretraining-language-models-with-human#ran","syntology_url":"https://syntology.ai/paper/2302.08582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08582"}},"official":{"repos":["tomekkorbak/pretraining-with-human-feedback"],"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":["found_in_text","official"]}}},{"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-simulate-daily-activities-via","slug":"learning-to-simulate-daily-activities-via","title":"Learning to Simulate Daily Activities via Modeling Dynamic Human Needs","date":"2023-02-09","arxiv_id":"2302.10897","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/learning-to-simulate-daily-activities-via#ran","syntology_url":"https://syntology.ai/paper/2302.10897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10897"}},"official":{"repos":["tsinghua-fib-lab/sand"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/target-based-surrogates-for-stochastic","slug":"target-based-surrogates-for-stochastic","title":"Target-based Surrogates for Stochastic Optimization","date":"2023-02-06","arxiv_id":"2302.02607","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/target-based-surrogates-for-stochastic#ran","syntology_url":"https://syntology.ai/paper/2302.02607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02607"}},"official":{"repos":["wilderlavington/target-based-surrogates-for-stochastic-optimization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"ea674ef81b550becb5d3d35ae7bc9309cd0acd278996dfb5010a457b2b25d72a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}