{"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/vision-language-action","name":"Vision-Language-Action","slug":"vision-language-action","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":157,"papers_with_code":49,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/automotiveui-bench-4k","name":"AutomotiveUI-Bench-4K","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/vision-language-navigation","name":"Vision-Language Navigation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":157,"of_with_code":49,"tagged_in_all":157,"counts":{"archive_papers_tagged":157,"with_a_code_link":49,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":157,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":23,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":23,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"items":[{"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":7,"n_instrument":1,"n_unverified":2,"n_honours":1,"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; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 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/vision-language-action-models-in-robotic","slug":"vision-language-action-models-in-robotic","title":"Vision Language Action Models in Robotic Manipulation: A Systematic Review","date":"2025-07-14","arxiv_id":"2507.10672","repositories_listed":1,"syntology":null},{"url":"/paper/vote-vision-language-action-optimization-with","slug":"vote-vision-language-action-optimization-with","title":"VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting","date":"2025-07-07","arxiv_id":"2507.05116","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vote-vision-language-action-optimization-with#ran","syntology_url":"https://syntology.ai/paper/2507.05116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.05116"}},"official":{"repos":["LukeLIN-web/VOTE"],"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/dreamvla-a-vision-language-action-model-1","slug":"dreamvla-a-vision-language-action-model-1","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","date":"2025-07-06","arxiv_id":"2507.04447","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dreamvla-a-vision-language-action-model-1#ran","syntology_url":"https://syntology.ai/paper/2507.04447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04447"}},"official":{"repos":["Zhangwenyao1/DreamVLA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-vision-language-action-models-for-1","slug":"a-survey-on-vision-language-action-models-for-1","title":"A Survey on Vision-Language-Action Models for Autonomous Driving","date":"2025-06-30","arxiv_id":"2506.24044","repositories_listed":1,"syntology":null},{"url":"/paper/parallels-between-vla-model-post-training-and","slug":"parallels-between-vla-model-post-training-and","title":"Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends","date":"2025-06-26","arxiv_id":"2506.20966","repositories_listed":1,"syntology":null},{"url":"/paper/worldvla-towards-autoregressive-action-world","slug":"worldvla-towards-autoregressive-action-world","title":"WorldVLA: Towards Autoregressive Action World Model","date":"2025-06-26","arxiv_id":"2506.21539","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/worldvla-towards-autoregressive-action-world#ran","syntology_url":"https://syntology.ai/paper/2506.21539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21539"}},"official":{"repos":["alibaba-damo-academy/worldvla"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comprehensive-survey-on-continual-learning","slug":"a-comprehensive-survey-on-continual-learning","title":"A Comprehensive Survey on Continual Learning in Generative Models","date":"2025-06-16","arxiv_id":"2506.13045","repositories_listed":1,"syntology":null},{"url":"/paper/autovla-a-vision-language-action-model-for","slug":"autovla-a-vision-language-action-model-for","title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","date":"2025-06-16","arxiv_id":"2506.13757","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/autovla-a-vision-language-action-model-for#ran","syntology_url":"https://syntology.ai/paper/2506.13757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13757"}},"official":{"repos":["ucla-mobility/AutoVLA"],"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/bitvla-1-bit-vision-language-action-models","slug":"bitvla-1-bit-vision-language-action-models","title":"BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation","date":"2025-06-09","arxiv_id":"2506.07530","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-execution-of-action-chunking-flow","slug":"real-time-execution-of-action-chunking-flow","title":"Real-Time Execution of Action Chunking Flow Policies","date":"2025-06-09","arxiv_id":"2506.07339","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/real-time-execution-of-action-chunking-flow#ran","syntology_url":"https://syntology.ai/paper/2506.07339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07339"}},"official":{"repos":["Physical-Intelligence/real-time-chunking-kinetix"],"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/surgeon-style-fingerprinting-and-privacy-risk","slug":"surgeon-style-fingerprinting-and-privacy-risk","title":"Surgeon Style Fingerprinting and Privacy Risk Quantification via Discrete Diffusion Models in a Vision-Language-Action Framework","date":"2025-06-09","arxiv_id":"2506.08185","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attacks-on-robotic-vision","slug":"adversarial-attacks-on-robotic-vision","title":"Adversarial Attacks on Robotic Vision Language Action Models","date":"2025-06-03","arxiv_id":"2506.03350","repositories_listed":1,"syntology":null},{"url":"/paper/smolvla-a-vision-language-action-model-for","slug":"smolvla-a-vision-language-action-model-for","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","date":"2025-06-02","arxiv_id":"2506.01844","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/smolvla-a-vision-language-action-model-for#ran","syntology_url":"https://syntology.ai/paper/2506.01844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01844"}},"official":{"repos":["huggingface/lerobot"],"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/impromptu-vla-open-weights-and-open-data-for","slug":"impromptu-vla-open-weights-and-open-data-for","title":"Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models","date":"2025-05-29","arxiv_id":"2505.23757","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-action-model-with-open-world","slug":"vision-language-action-model-with-open-world","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","date":"2025-05-28","arxiv_id":"2505.21906","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 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/vla-rl-towards-masterful-and-general-robotic","slug":"vla-rl-towards-masterful-and-general-robotic","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","date":"2025-05-24","arxiv_id":"2505.18719","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/vla-rl-towards-masterful-and-general-robotic#ran","syntology_url":"https://syntology.ai/paper/2505.18719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18719"}},"official":{"repos":["guanxinglu/vlarl"],"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/perceptual-quality-assessment-for-embodied-ai","slug":"perceptual-quality-assessment-for-embodied-ai","title":"Perceptual Quality Assessment for Embodied AI","date":"2025-05-22","arxiv_id":"2505.16815","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-limits-of-vision-language","slug":"exploring-the-limits-of-vision-language","title":"Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization","date":"2025-05-21","arxiv_id":"2505.15660","repositories_listed":1,"syntology":null},{"url":"/paper/robofac-a-comprehensive-framework-for-robotic","slug":"robofac-a-comprehensive-framework-for-robotic","title":"RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction","date":"2025-05-18","arxiv_id":"2505.12224","repositories_listed":1,"syntology":null},{"url":"/paper/from-seeing-to-doing-bridging-reasoning-and","slug":"from-seeing-to-doing-bridging-reasoning-and","title":"From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation","date":"2025-05-13","arxiv_id":"2505.08548","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":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) · 2 unverified","sample_list":"/paper/from-seeing-to-doing-bridging-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2505.08548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.08548"}},"official":{"repos":["pickxiguapi/embodied-fsd"],"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/univla-learning-to-act-anywhere-with-task","slug":"univla-learning-to-act-anywhere-with-task","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","date":"2025-05-09","arxiv_id":"2505.06111","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/univla-learning-to-act-anywhere-with-task#ran","syntology_url":"https://syntology.ai/paper/2505.06111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.06111"}},"official":{"repos":["opendrivelab/univla"],"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/benchmarking-vision-language-action-models-in","slug":"benchmarking-vision-language-action-models-in","title":"Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environments","date":"2025-05-08","arxiv_id":"2505.05540","repositories_listed":1,"syntology":null},{"url":"/paper/openhelix-a-short-survey-empirical-analysis","slug":"openhelix-a-short-survey-empirical-analysis","title":"OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation","date":"2025-05-06","arxiv_id":"2505.03912","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/openhelix-a-short-survey-empirical-analysis#ran","syntology_url":"https://syntology.ai/paper/2505.03912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.03912"}},"official":{"repos":["OpenHelix-robot/OpenHelix"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/gui-r1-a-generalist-r1-style-vision-language","slug":"gui-r1-a-generalist-r1-style-vision-language","title":"GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents","date":"2025-04-14","arxiv_id":"2504.10458","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gui-r1-a-generalist-r1-style-vision-language#ran","syntology_url":"https://syntology.ai/paper/2504.10458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10458"}},"official":null}},{"url":"/paper/opendrivevla-towards-end-to-end-autonomous","slug":"opendrivevla-towards-end-to-end-autonomous","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","date":"2025-03-30","arxiv_id":"2503.23463","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/opendrivevla-towards-end-to-end-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.23463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23463"}},"official":{"repos":["DriveVLA/OpenDriveVLA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dita-scaling-diffusion-transformer-for","slug":"dita-scaling-diffusion-transformer-for","title":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy","date":"2025-03-25","arxiv_id":"2503.19757","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dita-scaling-diffusion-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2503.19757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19757"}},"official":null}},{"url":"/paper/combatvla-an-efficient-vision-language-action","slug":"combatvla-an-efficient-vision-language-action","title":"CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games","date":"2025-03-12","arxiv_id":"2503.09527","repositories_listed":1,"syntology":null},{"url":"/paper/pointvla-injecting-the-3d-world-into-vision","slug":"pointvla-injecting-the-3d-world-into-vision","title":"PointVLA: Injecting the 3D World into Vision-Language-Action Models","date":"2025-03-10","arxiv_id":"2503.07511","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 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/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/chatvla-unified-multimodal-understanding-and","slug":"chatvla-unified-multimodal-understanding-and","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model","date":"2025-02-20","arxiv_id":"2502.14420","repositories_listed":1,"syntology":null},{"url":"/paper/dexvla-vision-language-model-with-plug-in","slug":"dexvla-vision-language-model-with-plug-in","title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","date":"2025-02-09","arxiv_id":"2502.05855","repositories_listed":1,"syntology":null},{"url":"/paper/conrft-a-reinforced-fine-tuning-method-for","slug":"conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","date":"2025-02-08","arxiv_id":"2502.05450","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conrft-a-reinforced-fine-tuning-method-for#ran","syntology_url":"https://syntology.ai/paper/2502.05450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05450"}},"official":{"repos":["cccedric/conrft"],"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/uav-vla-vision-language-action-system-for","slug":"uav-vla-vision-language-action-system-for","title":"UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation","date":"2025-01-09","arxiv_id":"2501.05014","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generalist-robot-policies-what","slug":"towards-generalist-robot-policies-what","title":"Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models","date":"2024-12-18","arxiv_id":"2412.14058","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-generalist-robot-policies-what#ran","syntology_url":"https://syntology.ai/paper/2412.14058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14058"}},"official":null}},{"url":"/paper/robomatrix-a-skill-centric-hierarchical","slug":"robomatrix-a-skill-centric-hierarchical","title":"RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World","date":"2024-11-29","arxiv_id":"2412.00171","repositories_listed":1,"syntology":null},{"url":"/paper/showui-one-vision-language-action-model-for","slug":"showui-one-vision-language-action-model-for","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","date":"2024-11-26","arxiv_id":"2411.17465","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/showui-one-vision-language-action-model-for#ran","syntology_url":"https://syntology.ai/paper/2411.17465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17465"}},"official":{"repos":["showlab/showui"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-the-adversarial-vulnerabilities-of","slug":"exploring-the-adversarial-vulnerabilities-of","title":"Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics","date":"2024-11-18","arxiv_id":"2411.13587","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-vision-language-action-models-on","slug":"benchmarking-vision-language-action-models-on","title":"Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks","date":"2024-11-04","arxiv_id":"2411.05821","repositories_listed":1,"syntology":null},{"url":"/paper/deer-vla-dynamic-inference-of-multimodal","slug":"deer-vla-dynamic-inference-of-multimodal","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","date":"2024-11-04","arxiv_id":"2411.02359","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/deer-vla-dynamic-inference-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2411.02359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02359"}},"official":{"repos":["yueyang130/deer-vla"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-transformer-policy","slug":"diffusion-transformer-policy","title":"Diffusion Transformer Policy","date":"2024-10-21","arxiv_id":"2410.15959","repositories_listed":1,"syntology":null},{"url":"/paper/latent-action-pretraining-from-videos","slug":"latent-action-pretraining-from-videos","title":"Latent Action Pretraining from Videos","date":"2024-10-15","arxiv_id":"2410.11758","repositories_listed":1,"syntology":{"n":36,"n_ran":30,"n_constructed":0,"n_ran_checked":18,"n_instrument":12,"n_unverified":6,"n_honours":4,"n_violates":5,"n_no_contract":9,"n_pointer_only":4,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 5 violated, 9 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/latent-action-pretraining-from-videos#ran","syntology_url":"https://syntology.ai/paper/2410.11758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11758"}},"official":null}},{"url":"/paper/tinyvla-towards-fast-data-efficient-vision","slug":"tinyvla-towards-fast-data-efficient-vision","title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","date":"2024-09-19","arxiv_id":"2409.12514","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/tinyvla-towards-fast-data-efficient-vision#ran","syntology_url":"https://syntology.ai/paper/2409.12514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12514"}},"official":null}},{"url":"/paper/llara-supercharging-robot-learning-data-for","slug":"llara-supercharging-robot-learning-data-for","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","date":"2024-06-28","arxiv_id":"2406.20095","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llara-supercharging-robot-learning-data-for#ran","syntology_url":"https://syntology.ai/paper/2406.20095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20095"}},"official":{"repos":["lostxine/llara"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-meets-the-skeleton","slug":"vision-language-meets-the-skeleton","title":"Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning","date":"2024-05-31","arxiv_id":"2405.20606","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-vision-language-action-models-for","slug":"a-survey-on-vision-language-action-models-for","title":"A Survey on Vision-Language-Action Models for Embodied AI","date":"2024-05-23","arxiv_id":"2405.14093","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-language-vision-and-action","slug":"bridging-language-vision-and-action","title":"Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks","date":"2024-04-02","arxiv_id":"2404.01932","repositories_listed":1,"syntology":null},{"url":"/paper/an-embodied-generalist-agent-in-3d-world","slug":"an-embodied-generalist-agent-in-3d-world","title":"An Embodied Generalist Agent in 3D World","date":"2023-11-18","arxiv_id":"2311.12871","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-embodied-generalist-agent-in-3d-world#ran","syntology_url":"https://syntology.ai/paper/2311.12871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12871"}},"official":{"repos":["embodied-generalist/embodied-generalist"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rt-2-vision-language-action-models-transfer","slug":"rt-2-vision-language-action-models-transfer","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","date":"2023-07-28","arxiv_id":"2307.15818","repositories_listed":1,"syntology":null},{"url":null,"slug":"anypos-automated-task-agnostic-actions-for","title":"AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation","date":"2025-07-17","arxiv_id":"2507.12768","repositories_listed":0,"syntology":null},{"url":null,"slug":"laviplan-language-guided-visual-path-planning","title":"LaViPlan : Language-Guided Visual Path Planning with RLVR","date":"2025-07-17","arxiv_id":"2507.12911","repositories_listed":0,"syntology":null},{"url":null,"slug":"cronusvla-transferring-latent-motion-across","title":"CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation","date":"2025-06-24","arxiv_id":"2506.19816","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-vision-language-action-model","title":"Unified Vision-Language-Action Model","date":"2025-06-24","arxiv_id":"2506.19850","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlrc-reinforcement-learning-based-recovery","title":"RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17639","repositories_listed":0,"syntology":null},{"url":null,"slug":"robomonkey-scaling-test-time-sampling-and","title":"RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17811","repositories_listed":0,"syntology":null},{"url":null,"slug":"vla-os-structuring-and-dissecting-planning","title":"VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17561","repositories_listed":0,"syntology":null},{"url":null,"slug":"capsdt-diffusion-transformer-for-capsule","title":"CapsDT: Diffusion-Transformer for Capsule Robot Manipulation","date":"2025-06-19","arxiv_id":"2506.16263","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-wise-adaptive-caching-for-accelerating","title":"Block-wise Adaptive Caching for Accelerating Diffusion Policy","date":"2025-06-16","arxiv_id":"2506.13456","repositories_listed":0,"syntology":null},{"url":null,"slug":"leverb-humanoid-whole-body-control-with","title":"LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction","date":"2025-06-16","arxiv_id":"2506.13751","repositories_listed":0,"syntology":null},{"url":null,"slug":"rosa-harnessing-robot-states-for-vision","title":"ROSA: Harnessing Robot States for Vision-Language and Action Alignment","date":"2025-06-16","arxiv_id":"2506.13679","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficientvla-training-free-acceleration-and","title":"EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models","date":"2025-06-11","arxiv_id":"2506.10100","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-intention-to-execution-probing-the","title":"From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models","date":"2025-06-11","arxiv_id":"2506.09930","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-multitask-failure-detection-for-vision","title":"SAFE: Multitask Failure Detection for Vision-Language-Action Models","date":"2025-06-11","arxiv_id":"2506.09937","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08462","title":"Hybrid Reasoning for Perception, Explanation, and Autonomous Action in Manufacturing","date":"2025-06-10","arxiv_id":"2506.08462","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08822","title":"FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency","date":"2025-06-10","arxiv_id":"2506.08822","repositories_listed":0,"syntology":null},{"url":"/paper/an-open-source-software-toolkit-benchmark","slug":"an-open-source-software-toolkit-benchmark","title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models","date":"2025-06-10","arxiv_id":"2506.09172","repositories_listed":0,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 3 unverified","sample_list":"/paper/an-open-source-software-toolkit-benchmark#ran","syntology_url":"https://syntology.ai/paper/2506.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09172"}},"official":null}},{"url":null,"slug":"tgrpo-fine-tuning-vision-language-action","title":"TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization","date":"2025-06-10","arxiv_id":"2506.08440","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridgevla-input-output-alignment-for","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models","date":"2025-06-09","arxiv_id":"2506.07961","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-policy-learning-via-human-assisted","title":"Robotic Policy Learning via Human-assisted Action Preference Optimization","date":"2025-06-08","arxiv_id":"2506.07127","repositories_listed":0,"syntology":null},{"url":null,"slug":"robocerebra-a-large-scale-benchmark-for-long","title":"RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation","date":"2025-06-07","arxiv_id":"2506.06677","repositories_listed":0,"syntology":null},{"url":null,"slug":"driveaction-a-benchmark-for-exploring-human","title":"DriveAction: A Benchmark for Exploring Human-like Driving Decisions in VLA Models","date":"2025-06-06","arxiv_id":"2506.05667","repositories_listed":0,"syntology":null},{"url":null,"slug":"reagent-v-a-reward-driven-multi-agent","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","date":"2025-06-02","arxiv_id":"2506.01300","repositories_listed":0,"syntology":null},{"url":null,"slug":"og-vla-3d-aware-vision-language-action-model","title":"OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation","date":"2025-06-01","arxiv_id":"2506.01196","repositories_listed":0,"syntology":null},{"url":null,"slug":"lohovla-a-unified-vision-language-action","title":"LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks","date":"2025-05-31","arxiv_id":"2506.00411","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-generalizable-bimanual-foundation","title":"Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction","date":"2025-05-30","arxiv_id":"2505.24156","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-insulating-vision-language-action","title":"Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better","date":"2025-05-29","arxiv_id":"2505.23705","repositories_listed":0,"syntology":null},{"url":null,"slug":"trackvla-embodied-visual-tracking-in-the-wild","title":"TrackVLA: Embodied Visual Tracking in the Wild","date":"2025-05-29","arxiv_id":"2505.23189","repositories_listed":0,"syntology":null},{"url":null,"slug":"forcevla-enhancing-vla-models-with-a-force","title":"ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation","date":"2025-05-28","arxiv_id":"2505.22159","repositories_listed":0,"syntology":null},{"url":null,"slug":"hume-introducing-system-2-thinking-in-visual","title":"Hume: Introducing System-2 Thinking in Visual-Language-Action Model","date":"2025-05-27","arxiv_id":"2505.21432","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-ai-with-foundation-models-for-mobile","title":"Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review","date":"2025-05-26","arxiv_id":"2505.20503","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-can-rl-bring-to-vla-generalization-an","title":"What Can RL Bring to VLA Generalization? An Empirical Study","date":"2025-05-26","arxiv_id":"2505.19789","repositories_listed":0,"syntology":null},{"url":null,"slug":"badvla-towards-backdoor-attacks-on-vision","title":"BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization","date":"2025-05-22","arxiv_id":"2505.16640","repositories_listed":0,"syntology":null},{"url":"/paper/drivemoe-mixture-of-experts-for-vision","slug":"drivemoe-mixture-of-experts-for-vision","title":"DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving","date":"2025-05-22","arxiv_id":"2505.16278","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-post-training-for-vision-language","title":"Interactive Post-Training for Vision-Language-Action Models","date":"2025-05-22","arxiv_id":"2505.17016","repositories_listed":0,"syntology":null},{"url":null,"slug":"endovla-dual-phase-vision-language-action","title":"EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy","date":"2025-05-21","arxiv_id":"2505.15206","repositories_listed":0,"syntology":null},{"url":null,"slug":"flare-robot-learning-with-implicit-world","title":"FLARE: Robot Learning with Implicit World Modeling","date":"2025-05-21","arxiv_id":"2505.15659","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-focus-actor-for-data-efficient-robot","title":"Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation","date":"2025-05-21","arxiv_id":"2505.15098","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditioning-matters-training-diffusion","title":"Conditioning Matters: Training Diffusion Policies is Faster Than You Think","date":"2025-05-16","arxiv_id":"2505.11123","repositories_listed":0,"syntology":null},{"url":null,"slug":"rt-cache-efficient-robot-trajectory-retrieval","title":"RT-cache: Efficient Robot Trajectory Retrieval System","date":"2025-05-14","arxiv_id":"2505.09040","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixel-motion-as-universal-representation-for","title":"Pixel Motion as Universal Representation for Robot Control","date":"2025-05-12","arxiv_id":"2505.07817","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-cavla-leveraging-depth-and-3d-context-to","title":"3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks","date":"2025-05-09","arxiv_id":"2505.05800","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-action-models-concepts","title":"Vision-Language-Action Models: Concepts, Progress, Applications and Challenges","date":"2025-05-07","arxiv_id":"2505.04769","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-data-curation-using-gps-nlp-to","title":"Automated Data Curation Using GPS & NLP to Generate Instruction-Action Pairs for Autonomous Vehicle Vision-Language Navigation Datasets","date":"2025-05-06","arxiv_id":"2505.03174","repositories_listed":0,"syntology":null},{"url":null,"slug":"nora-a-small-open-sourced-generalist-vision","title":"NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks","date":"2025-04-28","arxiv_id":"2504.19854","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-0-5-a-vision-language-action-model-with","title":"$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","date":"2025-04-22","arxiv_id":"2504.16054","repositories_listed":0,"syntology":null},{"url":null,"slug":"opal-encoding-causal-understanding-of","title":"OPAL: Encoding Causal Understanding of Physical Systems for Robot Learning","date":"2025-04-09","arxiv_id":"2504.06538","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-multimodal-llms-to-embodied-agents","title":"Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning","date":"2025-04-01","arxiv_id":"2504.00907","repositories_listed":0,"syntology":null},{"url":null,"slug":"cot-vla-visual-chain-of-thought-reasoning-for","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","date":"2025-03-27","arxiv_id":"2503.22020","repositories_listed":0,"syntology":null},{"url":null,"slug":"mole-vla-dynamic-layer-skipping-vision","title":"MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation","date":"2025-03-26","arxiv_id":"2503.20384","repositories_listed":0,"syntology":null},{"url":null,"slug":"dataplatter-boosting-robotic-manipulation","title":"DataPlatter: Boosting Robotic Manipulation Generalization with Minimal Costly Data","date":"2025-03-25","arxiv_id":"2503.19516","repositories_listed":0,"syntology":null}],"syntology_records":26,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":26,"papers_where_code_ran_first_page":"/task/vision-language-action/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/vision-language-action/papers/2","json":"/task/vision-language-action/papers/2.json","rows":57},{"order":"ran","page":1,"of":1,"url":"/task/vision-language-action/papers/ran/1","json":"/task/vision-language-action/papers/ran/1.json","rows":26}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"50e9e8873e492f268085e4f5d0ceb6ad099e310f7daaad8ea34bc0b8143b6519","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}