{"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/action-generation","name":"Action Generation","slug":"action-generation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":111,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/humanact12","name":"HumanAct12","full_name":"","num_papers_in_archive":37},{"url":"/dataset/phspd","name":"PHSPD","full_name":"Polarization Human Shape and Pose Dataset","num_papers_in_archive":2},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1},{"url":"/dataset/two4two","name":"Two4Two","full_name":"A Synthetic Dataset For Controlled Experiments","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/human-action-generation","name":"Human action generation"}],"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":111,"of_with_code":49,"tagged_in_all":111,"counts":{"archive_papers_tagged":111,"with_a_code_link":49,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":111,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/mapping-instructions-to-actions-in-3d","slug":"mapping-instructions-to-actions-in-3d","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","date":"2018-09-04","arxiv_id":"1809.00786","repositories_listed":5,"syntology":null},{"url":"/paper/infigui-r1-advancing-multimodal-gui-agents","slug":"infigui-r1-advancing-multimodal-gui-agents","title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","date":"2025-04-19","arxiv_id":"2504.14239","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infigui-r1-advancing-multimodal-gui-agents#ran","syntology_url":"https://syntology.ai/paper/2504.14239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14239"}},"official":{"repos":["reallm-labs/infigui-r1"],"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/flow-q-learning","slug":"flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","arxiv_id":"2502.02538","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-q-learning#ran","syntology_url":"https://syntology.ai/paper/2502.02538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02538"}},"official":{"repos":["seohongpark/fql"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/autocrawler-a-progressive-understanding-web","slug":"autocrawler-a-progressive-understanding-web","title":"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation","date":"2024-04-19","arxiv_id":"2404.12753","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/autocrawler-a-progressive-understanding-web#ran","syntology_url":"https://syntology.ai/paper/2404.12753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12753"}},"official":{"repos":["ez-hwh/autocrawler","ez-hwh/autoscraper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/human-action-generation-with-generative","slug":"human-action-generation-with-generative","title":"Human Action Generation with Generative Adversarial Networks","date":"2018-05-26","arxiv_id":"1805.10416","repositories_listed":2,"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/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/time-to-talk-llm-agents-for-asynchronous","slug":"time-to-talk-llm-agents-for-asynchronous","title":"Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games","date":"2025-06-05","arxiv_id":"2506.05309","repositories_listed":1,"syntology":null},{"url":"/paper/owmm-agent-open-world-mobile-manipulation","slug":"owmm-agent-open-world-mobile-manipulation","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis","date":"2025-06-04","arxiv_id":"2506.04217","repositories_listed":1,"syntology":null},{"url":"/paper/star-learning-diverse-robot-skill","slug":"star-learning-diverse-robot-skill","title":"STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization","date":"2025-06-04","arxiv_id":"2506.03863","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/distilling-llm-agent-into-small-models-with","slug":"distilling-llm-agent-into-small-models-with","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","date":"2025-05-23","arxiv_id":"2505.17612","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/distilling-llm-agent-into-small-models-with#ran","syntology_url":"https://syntology.ai/paper/2505.17612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17612"}},"official":{"repos":["nardien/agent-distillation"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-explorer-towards-efficient-and-affordable","slug":"llm-explorer-towards-efficient-and-affordable","title":"LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps","date":"2025-05-15","arxiv_id":"2505.10593","repositories_listed":1,"syntology":null},{"url":"/paper/train-a-multi-task-diffusion-policy-on","slug":"train-a-multi-task-diffusion-policy-on","title":"Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batches","date":"2025-05-14","arxiv_id":"2505.09430","repositories_listed":1,"syntology":null},{"url":"/paper/prior-does-matter-visual-navigation-via","slug":"prior-does-matter-visual-navigation-via","title":"Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models","date":"2025-04-14","arxiv_id":"2504.10041","repositories_listed":1,"syntology":null},{"url":"/paper/agent-models-internalizing-chain-of-action","slug":"agent-models-internalizing-chain-of-action","title":"Agent models: Internalizing Chain-of-Action Generation into Reasoning models","date":"2025-03-09","arxiv_id":"2503.06580","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/agent-models-internalizing-chain-of-action#ran","syntology_url":"https://syntology.ai/paper/2503.06580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06580"}},"official":{"repos":["adam-bjtu/autocoa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/litewebagent-the-open-source-suite-for-vlm","slug":"litewebagent-the-open-source-suite-for-vlm","title":"LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications","date":"2025-03-04","arxiv_id":"2503.02950","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-a-good-diffusion-planner-for","slug":"what-makes-a-good-diffusion-planner-for","title":"What Makes a Good Diffusion Planner for Decision Making?","date":"2025-03-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-vision-language-action-models","slug":"fine-tuning-vision-language-action-models","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","date":"2025-02-27","arxiv_id":"2502.19645","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-tuning-vision-language-action-models#ran","syntology_url":"https://syntology.ai/paper/2502.19645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19645"}},"official":null}},{"url":"/paper/pmat-optimizing-action-generation-order-in","slug":"pmat-optimizing-action-generation-order-in","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16496","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-multi-robot-systems","slug":"large-language-models-for-multi-robot-systems","title":"Large Language Models for Multi-Robot Systems: A Survey","date":"2025-02-06","arxiv_id":"2502.03814","repositories_listed":1,"syntology":null},{"url":"/paper/large-action-models-from-inception-to","slug":"large-action-models-from-inception-to","title":"Large Action Models: From Inception to Implementation","date":"2024-12-13","arxiv_id":"2412.10047","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/seg2act-global-context-aware-action","slug":"seg2act-global-context-aware-action","title":"Seg2Act: Global Context-aware Action Generation for Document Logical Structuring","date":"2024-10-09","arxiv_id":"2410.06802","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":2,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/seg2act-global-context-aware-action#ran","syntology_url":"https://syntology.ai/paper/2410.06802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06802"}},"official":{"repos":["cascip/seg2act"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/affordance-based-robot-manipulation-with-flow","slug":"affordance-based-robot-manipulation-with-flow","title":"Affordance-based Robot Manipulation with Flow Matching","date":"2024-09-02","arxiv_id":"2409.01083","repositories_listed":1,"syntology":null},{"url":"/paper/epo-hierarchical-llm-agents-with-environment","slug":"epo-hierarchical-llm-agents-with-environment","title":"EPO: Hierarchical LLM Agents with Environment Preference Optimization","date":"2024-08-28","arxiv_id":"2408.16090","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/epo-hierarchical-llm-agents-with-environment#ran","syntology_url":"https://syntology.ai/paper/2408.16090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16090"}},"official":{"repos":["kevinz8866/epo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-robotics-problems-in-zero-shot-with","slug":"solving-robotics-problems-in-zero-shot-with","title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","date":"2024-07-26","arxiv_id":"2407.19094","repositories_listed":1,"syntology":null},{"url":"/paper/echoreel-enhancing-action-generation-of","slug":"echoreel-enhancing-action-generation-of","title":"AICL: Action In-Context Learning for Video Diffusion Model","date":"2024-03-18","arxiv_id":"2403.11535","repositories_listed":1,"syntology":null},{"url":"/paper/pokellmon-a-human-parity-agent-for-pokemon","slug":"pokellmon-a-human-parity-agent-for-pokemon","title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01118","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-compositional-graph-convolutional","slug":"dynamic-compositional-graph-convolutional","title":"Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction","date":"2023-11-23","arxiv_id":"2311.13781","repositories_listed":1,"syntology":null},{"url":"/paper/driving-with-llms-fusing-object-level-vector","slug":"driving-with-llms-fusing-object-level-vector","title":"Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","date":"2023-10-03","arxiv_id":"2310.01957","repositories_listed":1,"syntology":null},{"url":"/paper/act-empowering-decision-transformer-with","slug":"act-empowering-decision-transformer-with","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","date":"2023-09-12","arxiv_id":"2309.05915","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/act-empowering-decision-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2309.05915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05915"}},"official":{"repos":["lamda-rl/act"],"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/jotr-a-joint-transformer-and-reinforcement","slug":"jotr-a-joint-transformer-and-reinforcement","title":"JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning","date":"2023-09-01","arxiv_id":"2309.00230","repositories_listed":1,"syntology":null},{"url":"/paper/language-free-compositional-action-generation","slug":"language-free-compositional-action-generation","title":"Language-free Compositional Action Generation via Decoupling Refinement","date":"2023-07-07","arxiv_id":"2307.03538","repositories_listed":1,"syntology":null},{"url":"/paper/flag3d-a-3d-fitness-activity-dataset-with","slug":"flag3d-a-3d-fitness-activity-dataset-with","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","date":"2022-12-09","arxiv_id":"2212.04638","repositories_listed":1,"syntology":null},{"url":"/paper/learning-physically-realizable-skills-for","slug":"learning-physically-realizable-skills-for","title":"Learning Physically Realizable Skills for Online Packing of General 3D Shapes","date":"2022-12-05","arxiv_id":"2212.02094","repositories_listed":1,"syntology":null},{"url":"/paper/text-editing-as-imitation-game","slug":"text-editing-as-imitation-game","title":"Text Editing as Imitation Game","date":"2022-10-21","arxiv_id":"2210.12276","repositories_listed":1,"syntology":null},{"url":"/paper/comma-modeling-relationship-among-motivations","slug":"comma-modeling-relationship-among-motivations","title":"COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities","date":"2022-09-14","arxiv_id":"2209.06470","repositories_listed":1,"syntology":null},{"url":"/paper/cogintac-modeling-the-relationships-between","slug":"cogintac-modeling-the-relationships-between","title":"CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective","date":"2022-05-07","arxiv_id":"2205.03540","repositories_listed":1,"syntology":null},{"url":"/paper/translation-based-supervision-for-policy","slug":"translation-based-supervision-for-policy","title":"Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-adversarial-graph-convolutional","slug":"generative-adversarial-graph-convolutional","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","date":"2021-10-21","arxiv_id":"2110.11191","repositories_listed":1,"syntology":null},{"url":"/paper/mugl-large-scale-multi-person-conditional","slug":"mugl-large-scale-multi-person-conditional","title":"MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion","date":"2021-10-21","arxiv_id":"2110.11460","repositories_listed":1,"syntology":null},{"url":"/paper/keep-calm-and-explore-language-models-for","slug":"keep-calm-and-explore-language-models-for","title":"Keep CALM and Explore: Language Models for Action Generation in Text-based Games","date":"2020-10-06","arxiv_id":"2010.02903","repositories_listed":1,"syntology":null},{"url":"/paper/action2motion-conditioned-generation-of-3d","slug":"action2motion-conditioned-generation-of-3d","title":"Action2Motion: Conditioned Generation of 3D Human Motions","date":"2020-07-30","arxiv_id":"2007.15240","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/action2motion-conditioned-generation-of-3d#ran","syntology_url":"https://syntology.ai/paper/2007.15240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15240"}},"official":{"repos":["EricGuo5513/action-to-motion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structure-aware-human-action-generation","slug":"structure-aware-human-action-generation","title":"Structure-Aware Human-Action Generation","date":"2020-07-04","arxiv_id":"2007.01971","repositories_listed":1,"syntology":null},{"url":"/paper/graph-constrained-reinforcement-learning-for-1","slug":"graph-constrained-reinforcement-learning-for-1","title":"Graph Constrained Reinforcement Learning for Natural Language Action Spaces","date":"2020-01-23","arxiv_id":"2001.08837","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/graph-constrained-reinforcement-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2001.08837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08837"}},"official":{"repos":["rajammanabrolu/KG-A2C"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/learning-diverse-stochastic-human-action","slug":"learning-diverse-stochastic-human-action","title":"Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions","date":"2019-12-21","arxiv_id":"1912.10150","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-diverse-stochastic-human-action#ran","syntology_url":"https://syntology.ai/paper/1912.10150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.10150"}},"official":{"repos":["zheshiyige/Learning-Diverse-Stochastic-Human-Action-Generators-by-Learning-Smooth-Latent-Transitions"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-data-driven-approach-for-motion-planning-of","slug":"a-data-driven-approach-for-motion-planning-of","title":"Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer Optimization","date":"2019-04-18","arxiv_id":"1904.08784","repositories_listed":1,"syntology":null},{"url":null,"slug":"vita-vision-to-action-flow-matching-policy","title":"VITA: Vision-to-Action Flow Matching Policy","date":"2025-07-17","arxiv_id":"2507.13231","repositories_listed":0,"syntology":null},{"url":"/paper/flow-based-single-step-completion-for","slug":"flow-based-single-step-completion-for","title":"Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning","date":"2025-06-26","arxiv_id":"2506.21427","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flow-based-single-step-completion-for#ran","syntology_url":"https://syntology.ai/paper/2506.21427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21427"}},"official":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":"codediffuser-attention-enhanced-diffusion","title":"CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity","date":"2025-06-19","arxiv_id":"2506.16652","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":"time-unified-diffusion-policy-with-action","title":"Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation","date":"2025-06-11","arxiv_id":"2506.09422","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":"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":"hierarchical-instruction-aware-embodied","title":"Hierarchical Instruction-aware Embodied Visual Tracking","date":"2025-05-27","arxiv_id":"2505.20710","repositories_listed":0,"syntology":null},{"url":null,"slug":"prophetdwm-a-driving-world-model-for-rolling","title":"ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos","date":"2025-05-24","arxiv_id":"2505.18650","repositories_listed":0,"syntology":null},{"url":null,"slug":"finephys-fine-grained-human-action-generation","title":"FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance","date":"2025-05-19","arxiv_id":"2505.13437","repositories_listed":0,"syntology":null},{"url":null,"slug":"h-mathbf-3-dp-triply-hierarchical-diffusion","title":"H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning","date":"2025-05-12","arxiv_id":"2505.07819","repositories_listed":0,"syntology":null},{"url":null,"slug":"story2game-generating-almost-everything-in-an","title":"STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game","date":"2025-05-06","arxiv_id":"2505.03547","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-gui-agents-with-foundation-models","title":"A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning","date":"2025-04-29","arxiv_id":"2504.20464","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-listener-dyadic-facial-motion","title":"Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion","date":"2025-04-29","arxiv_id":"2504.20685","repositories_listed":0,"syntology":null},{"url":null,"slug":"speci-skill-prompts-based-hierarchical","title":"SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation","date":"2025-04-22","arxiv_id":"2504.15561","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-selection-and-skill-segmentation-via","title":"Modality Selection and Skill Segmentation via Cross-Modality Attention","date":"2025-04-20","arxiv_id":"2504.14573","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-m-llm-based-gui-agents","title":"A Survey on (M)LLM-Based GUI Agents","date":"2025-03-27","arxiv_id":"2504.13865","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-believability-accurate-human-behavior","title":"LLM Agents That Act Like Us: Accurate Human Behavior Simulation with Real-World Data","date":"2025-03-26","arxiv_id":"2503.20749","repositories_listed":0,"syntology":null},{"url":"/paper/orion-a-holistic-end-to-end-autonomous","slug":"orion-a-holistic-end-to-end-autonomous","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","date":"2025-03-25","arxiv_id":"2503.19755","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-with-eyes-from-language-reasoning-to","title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","date":"2025-03-23","arxiv_id":"2503.18071","repositories_listed":0,"syntology":null},{"url":null,"slug":"primal-physically-reactive-and-interactive","title":"PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning","date":"2025-03-21","arxiv_id":"2503.17544","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffuse-cloc-guided-diffusion-for-physics","title":"Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control","date":"2025-03-14","arxiv_id":"2503.11801","repositories_listed":0,"syntology":null},{"url":null,"slug":"tla-tactile-language-action-model-for-contact","title":"TLA: Tactile-Language-Action Model for Contact-Rich Manipulation","date":"2025-03-11","arxiv_id":"2503.08548","repositories_listed":0,"syntology":null},{"url":null,"slug":"frmd-fast-robot-motion-diffusion-with","title":"FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action Generation","date":"2025-03-03","arxiv_id":"2503.02048","repositories_listed":0,"syntology":null},{"url":null,"slug":"vdt-auto-end-to-end-autonomous-driving-with","title":"VDT-Auto: End-to-end Autonomous Driving with VLM-Guided Diffusion Transformers","date":"2025-02-27","arxiv_id":"2502.20108","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-are-web-ai-agents-more-vulnerable-than","title":"Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis","date":"2025-02-27","arxiv_id":"2502.20383","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolution-6-0-evolving-robotic-capabilities","title":"Evolution 6.0: Evolving Robotic Capabilities Through Generative Design","date":"2025-02-24","arxiv_id":"2502.17034","repositories_listed":0,"syntology":null},{"url":null,"slug":"salsa-rl-stability-analysis-in-the-latent","title":"SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning","date":"2025-02-21","arxiv_id":"2502.15512","repositories_listed":0,"syntology":null},{"url":null,"slug":"imle-policy-fast-and-sample-efficient","title":"IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation","date":"2025-02-17","arxiv_id":"2502.12371","repositories_listed":0,"syntology":null},{"url":null,"slug":"r2c-mapping-room-to-chessboard-to-unlock-llm","title":"R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"carp-visuomotor-policy-learning-via-coarse-to","title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction","date":"2024-12-09","arxiv_id":"2412.06782","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-next-generation-medical-agent-how-o1","title":"Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios","date":"2024-11-16","arxiv_id":"2411.14461","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-video-models-to-actions-through","title":"Grounding Video Models to Actions through Goal Conditioned Exploration","date":"2024-11-11","arxiv_id":"2411.07223","repositories_listed":0,"syntology":null},{"url":null,"slug":"actionflow-equivariant-accurate-and-efficient","title":"ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching","date":"2024-09-06","arxiv_id":"2409.04576","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-purpose-clothes-manipulation-with","title":"General-purpose Clothes Manipulation with Semantic Keypoints","date":"2024-08-15","arxiv_id":"2408.08160","repositories_listed":0,"syntology":null},{"url":null,"slug":"robots-can-multitask-too-integrating-a-memory","title":"Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation","date":"2024-07-18","arxiv_id":"2407.13505","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-code-generation-for-1","title":"Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft","date":"2024-06-25","arxiv_id":"2406.17553","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-brain-like-concepts-to-embodied","title":"Introducing Brain-like Concepts to Embodied Hand-crafted Dialog Management System","date":"2024-06-13","arxiv_id":"2406.08996","repositories_listed":0,"syntology":null},{"url":null,"slug":"t2lm-long-term-3d-human-motion-generation","title":"T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences","date":"2024-06-02","arxiv_id":"2406.00636","repositories_listed":0,"syntology":null},{"url":null,"slug":"itcma-a-generative-agent-based-on-a","title":"ITCMA: A Generative Agent Based on a Computational Consciousness Structure","date":"2024-03-29","arxiv_id":"2403.20097","repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-initialize-and-explore-an-effective","title":"Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning","date":"2024-02-28","arxiv_id":"2402.17978","repositories_listed":0,"syntology":null},{"url":null,"slug":"return-aligned-decision-transformer","title":"Return-Aligned Decision Transformer","date":"2024-02-06","arxiv_id":"2402.03923","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-generation-network-of-human-skeleton","title":"Active Generation Network of Human Skeleton for Action Recognition","date":"2024-01-30","arxiv_id":"2401.17086","repositories_listed":0,"syntology":null},{"url":null,"slug":"assistgui-task-oriented-pc-graphical-user","title":"AssistGUI: Task-Oriented PC Graphical User Interface Automation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-empowered-agent-based","title":"Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives","date":"2023-12-19","arxiv_id":"2312.11970","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-path-modeling-for-vision-and-language","title":"Masked Path Modeling for Vision-and-Language Navigation","date":"2023-05-23","arxiv_id":"2305.14268","repositories_listed":0,"syntology":null},{"url":null,"slug":"sinc-spatial-composition-of-3d-human-motions","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","date":"2023-04-20","arxiv_id":"2304.10417","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-gpt-leveraging-large-scale-language","title":"Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation","date":"2022-11-28","arxiv_id":"2211.15603","repositories_listed":0,"syntology":null},{"url":null,"slug":"jarvis-a-neuro-symbolic-commonsense-reasoning","title":"JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents","date":"2022-08-28","arxiv_id":"2208.13266","repositories_listed":0,"syntology":null}],"syntology_records":17,"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":15,"papers_where_code_ran_first_page":"/task/action-generation/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/action-generation/papers/2","json":"/task/action-generation/papers/2.json","rows":11},{"order":"ran","page":1,"of":1,"url":"/task/action-generation/papers/ran/1","json":"/task/action-generation/papers/ran/1.json","rows":15}],"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":"7d349b57a7a803c24df5655ce391d9d5eea1883947b3fd439ecdd72f150b62e3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}