{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/imitation-learning/papers/8","list_of":"/task/imitation-learning","task":"Imitation Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":22,"rows_per_page":100,"rows":[701,800],"of":2122,"counts":{"archive_papers_tagged":2122,"with_a_code_link":691,"where_syntology_ran_a_sample":234,"not_listed_spam_title":0,"listed":2122,"listed_where_code_ran":234,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":191,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":191,"listed_every_run_a_failure_of_syntologys_instrument":43,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/imitation-learning","prev":"/task/imitation-learning/papers/7","next":"/task/imitation-learning/papers/9","papers":[{"url":null,"slug":"human2locoman-learning-versatile-quadrupedal","title":"Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining","date":"2025-06-19","arxiv_id":"2506.16475","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-task-agnostic-skill-bases-to-uncover","title":"Learning Task-Agnostic Skill Bases to Uncover Motor Primitives in Animal Behaviors","date":"2025-06-18","arxiv_id":"2506.15190","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-instant-policy-leveraging-student-s-t","title":"Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation","date":"2025-06-18","arxiv_id":"2506.15157","repositories_listed":0,"syntology":null},{"url":null,"slug":"steering-robots-with-inference-time","title":"Steering Robots with Inference-Time Interactions","date":"2025-06-17","arxiv_id":"2506.14287","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-imitation-learning-for-contact","title":"A Survey on Imitation Learning for Contact-Rich Tasks in Robotics","date":"2025-06-16","arxiv_id":"2506.13498","repositories_listed":0,"syntology":null},{"url":null,"slug":"touch-begins-where-vision-ends-generalizable","title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","date":"2025-06-16","arxiv_id":"2506.13762","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-matters-in-learning-from-large-scale","title":"What Matters in Learning from Large-Scale Datasets for Robot Manipulation","date":"2025-06-16","arxiv_id":"2506.13536","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-by-analogy-ood-generalization-of","title":"Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence","date":"2025-06-15","arxiv_id":"2506.12678","repositories_listed":0,"syntology":null},{"url":null,"slug":"sail-faster-than-demonstration-execution-of","title":"SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies","date":"2025-06-13","arxiv_id":"2506.11948","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-robot-navigation-using-event-based","title":"Human-Robot Navigation using Event-based Cameras and Reinforcement Learning","date":"2025-06-12","arxiv_id":"2506.10790","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":"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":"2506-08795","title":"Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning","date":"2025-06-10","arxiv_id":"2506.08795","repositories_listed":0,"syntology":null},{"url":null,"slug":"uad-unsupervised-affordance-distillation-for","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","date":"2025-06-10","arxiv_id":"2506.09284","repositories_listed":0,"syntology":null},{"url":"/paper/recogdrive-a-reinforced-cognitive-framework","slug":"recogdrive-a-reinforced-cognitive-framework","title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","date":"2025-06-09","arxiv_id":"2506.08052","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-via-implicit-imitation","title":"Reinforcement Learning via Implicit Imitation Guidance","date":"2025-06-09","arxiv_id":"2506.07505","repositories_listed":0,"syntology":null},{"url":null,"slug":"spikepingpong-high-frequency-spike-vision","title":"SpikePingpong: High-Frequency Spike Vision-based Robot Learning for Precise Striking in Table Tennis Game","date":"2025-06-07","arxiv_id":"2506.06690","repositories_listed":0,"syntology":null},{"url":null,"slug":"beast-efficient-tokenization-of-b-splines","title":"BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning","date":"2025-06-06","arxiv_id":"2506.06072","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowoe-imitation-learning-with-flow-policy","title":"FlowOE: Imitation Learning with Flow Policy from Ensemble RL Experts for Optimal Execution under Heston Volatility and Concave Market Impacts","date":"2025-06-06","arxiv_id":"2506.05755","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dissection-trajectories-from-expert","title":"Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion","date":"2025-06-05","arxiv_id":"2506.04716","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgn-cirl-scene-graph-based-navigation-with","title":"SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning","date":"2025-06-04","arxiv_id":"2506.04505","repositories_listed":0,"syntology":null},{"url":null,"slug":"rodrigues-network-for-learning-robot-actions","title":"Rodrigues Network for Learning Robot Actions","date":"2025-06-03","arxiv_id":"2506.02618","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-adaptive-noise-and-dropout","title":"Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks","date":"2025-06-02","arxiv_id":"2506.01350","repositories_listed":0,"syntology":null},{"url":null,"slug":"womap-world-models-for-embodied-open","title":"WoMAP: World Models For Embodied Open-Vocabulary Object Localization","date":"2025-06-02","arxiv_id":"2506.01600","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-think-synergizing-reasoning-acting-and","title":"Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents","date":"2025-05-31","arxiv_id":"2506.00320","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-imitation-learning-for-dexterous","title":"Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey","date":"2025-05-30","arxiv_id":"2506.00098","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-dacer-algorithm-with-high-diffusion","title":"Enhanced DACER Algorithm with High Diffusion Efficiency","date":"2025-05-29","arxiv_id":"2505.23426","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotransfer-geometry-consistent-video","title":"RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer","date":"2025-05-29","arxiv_id":"2505.23171","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-compositional-behaviors-from","title":"Learning Compositional Behaviors from Demonstration and Language","date":"2025-05-28","arxiv_id":"2505.21981","repositories_listed":0,"syntology":null},{"url":null,"slug":"scizor-a-self-supervised-approach-to-data","title":"SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning","date":"2025-05-28","arxiv_id":"2505.22626","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-flow-policy-simplifying-diffusion","title":"Streaming Flow Policy: Simplifying diffusion$/$flow-matching policies by treating action trajectories as flow trajectories","date":"2025-05-28","arxiv_id":"2505.21851","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-action-enhanced","title":"Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning","date":"2025-05-27","arxiv_id":"2505.20962","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-robograsp-generalized-robotic","title":"Spatial RoboGrasp: Generalized Robotic Grasping Control Policy","date":"2025-05-27","arxiv_id":"2505.20814","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-knowledge-distillation-with-reward","title":"Online Knowledge Distillation with Reward Guidance","date":"2025-05-25","arxiv_id":"2505.18952","repositories_listed":0,"syntology":null},{"url":null,"slug":"misodice-multi-agent-imitation-from-unlabeled","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","date":"2025-05-24","arxiv_id":"2505.18595","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-imitation-learning-for-long","title":"Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space","date":"2025-05-23","arxiv_id":"2505.17389","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-manipulation-of-deformable-objects-in","title":"Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy","date":"2025-05-23","arxiv_id":"2505.17434","repositories_listed":0,"syntology":null},{"url":null,"slug":"progrm-build-better-gui-agents-with-progress","title":"ProgRM: Build Better GUI Agents with Progress Rewards","date":"2025-05-23","arxiv_id":"2505.18121","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-online-rl-fine-tuning-with-offline","title":"Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only","date":"2025-05-22","arxiv_id":"2505.16856","repositories_listed":0,"syntology":null},{"url":"/paper/raw2drive-reinforcement-learning-with-aligned","slug":"raw2drive-reinforcement-learning-with-aligned","title":"Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)","date":"2025-05-22","arxiv_id":"2505.16394","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":"learning-based-autonomous-oversteer-control","title":"Learning-based Autonomous Oversteer Control and Collision Avoidance","date":"2025-05-21","arxiv_id":"2505.15275","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-twinning-for-hybrid-control-of","title":"Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones","date":"2025-05-21","arxiv_id":"2505.18201","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-flow-colosseo-a-real-world-benchmark-for","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning","date":"2025-05-21","arxiv_id":"2505.15725","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-via-focused-satisficing","title":"Imitation Learning via Focused Satisficing","date":"2025-05-20","arxiv_id":"2505.14820","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-agent-distillation-for-large","title":"Structured Agent Distillation for Large Language Model","date":"2025-05-20","arxiv_id":"2505.13820","repositories_listed":0,"syntology":null},{"url":null,"slug":"kintwin-imitation-learning-with-torque-and","title":"KinTwin: Imitation Learning with Torque and Muscle Driven Biomechanical Models Enables Precise Replication of Able-Bodied and Impaired Movement from Markerless Motion Capture","date":"2025-05-19","arxiv_id":"2505.13436","repositories_listed":0,"syntology":null},{"url":null,"slug":"egodex-learning-dexterous-manipulation-from","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","date":"2025-05-16","arxiv_id":"2505.11709","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-visual-generalization-in-robot","title":"Zero-Shot Visual Generalization in Robot Manipulation","date":"2025-05-16","arxiv_id":"2505.11719","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-ril-interleaved-reinforcement-and","title":"IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning","date":"2025-05-15","arxiv_id":"2505.10442","repositories_listed":0,"syntology":null},{"url":null,"slug":"datamil-selecting-data-for-robot-imitation","title":"DataMIL: Selecting Data for Robot Imitation Learning with Datamodels","date":"2025-05-14","arxiv_id":"2505.09603","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-realizable-students-from","title":"Distilling Realizable Students from Unrealizable Teachers","date":"2025-05-14","arxiv_id":"2505.09546","repositories_listed":0,"syntology":null},{"url":null,"slug":"enerverse-ac-envisioning-embodied","title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","date":"2025-05-14","arxiv_id":"2505.09723","repositories_listed":0,"syntology":null},{"url":null,"slug":"foldnet-learning-generalizable-closed-loop","title":"FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis","date":"2025-05-14","arxiv_id":"2505.09109","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-for-adaptive-control-of-a","title":"Imitation Learning for Adaptive Control of a Virtual Soft Exoglove","date":"2025-05-14","arxiv_id":"2505.09099","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-long-context-diffusion-policies-via","title":"Learning Long-Context Diffusion Policies via Past-Token Prediction","date":"2025-05-14","arxiv_id":"2505.09561","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-multivariate-regression-qualitative","title":"Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model","date":"2025-05-14","arxiv_id":"2505.09308","repositories_listed":0,"syntology":null},{"url":null,"slug":"chicgrasp-imitation-learning-based-customized","title":"ChicGrasp: Imitation-Learning based Customized Dual-Jaw Gripper Control for Delicate, Irregular Bio-products Manipulation","date":"2025-05-13","arxiv_id":"2505.08986","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-like-humans-advancing-llm-reasoning","title":"Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation","date":"2025-05-13","arxiv_id":"2505.08364","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-matters-for-batch-online-reinforcement","title":"What Matters for Batch Online Reinforcement Learning in Robotics?","date":"2025-05-12","arxiv_id":"2505.08078","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-sim-cross-embodiment-learning-via-real-to","title":"X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real","date":"2025-05-11","arxiv_id":"2505.07096","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowhft-flow-policy-induced-optimal-high","title":"FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditions","date":"2025-05-09","arxiv_id":"2505.05784","repositories_listed":0,"syntology":null},{"url":null,"slug":"vin-nbv-a-view-introspection-network-for-next","title":"VIN-NBV: A View Introspection Network for Next-Best-View Selection for Resource-Efficient 3D Reconstruction","date":"2025-05-09","arxiv_id":"2505.06219","repositories_listed":0,"syntology":null},{"url":null,"slug":"clam-continuous-latent-action-models-for","title":"CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations","date":"2025-05-08","arxiv_id":"2505.04999","repositories_listed":0,"syntology":null},{"url":null,"slug":"cubedagger-improved-robustness-of-interactive","title":"CubeDAgger: Improved Robustness of Interactive Imitation Learning without Violation of Dynamic Stability","date":"2025-05-08","arxiv_id":"2505.04897","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-coda-diffusion-for-coordinated-dual-arm","title":"D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation","date":"2025-05-08","arxiv_id":"2505.04860","repositories_listed":0,"syntology":null},{"url":null,"slug":"primal-dual-algorithm-for-contextual","title":"Primal-dual algorithm for contextual stochastic combinatorial optimization","date":"2025-05-07","arxiv_id":"2505.04757","repositories_listed":0,"syntology":null},{"url":null,"slug":"amo-adaptive-motion-optimization-for-hyper","title":"AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control","date":"2025-05-06","arxiv_id":"2505.03738","repositories_listed":0,"syntology":null},{"url":null,"slug":"ergodic-generative-flows","title":"Ergodic Generative Flows","date":"2025-05-06","arxiv_id":"2505.03561","repositories_listed":0,"syntology":null},{"url":null,"slug":"rift-closed-loop-rl-fine-tuning-for-realistic","title":"RIFT: Closed-Loop RL Fine-Tuning for Realistic and Controllable Traffic Simulation","date":"2025-05-06","arxiv_id":"2505.03344","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-unreasonable-effectiveness-of-discrete","title":"The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning","date":"2025-05-06","arxiv_id":"2505.03296","repositories_listed":0,"syntology":null},{"url":null,"slug":"coupled-distributional-random-expert","title":"Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning","date":"2025-05-04","arxiv_id":"2505.02228","repositories_listed":0,"syntology":null},{"url":null,"slug":"falconwing-an-open-source-platform-for-ultra","title":"FalconWing: An Open-Source Platform for Ultra-Light Fixed-Wing Aircraft Research","date":"2025-05-02","arxiv_id":"2505.01383","repositories_listed":0,"syntology":null},{"url":null,"slug":"prism-projection-based-reward-integration-for","title":"PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations","date":"2025-04-29","arxiv_id":"2504.20520","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-capability-for-imitation","title":"Generalization Capability for Imitation Learning","date":"2025-04-25","arxiv_id":"2504.18538","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-learning-of-controllable-diverse","title":"Offline Learning of Controllable Diverse Behaviors","date":"2025-04-25","arxiv_id":"2504.18160","repositories_listed":0,"syntology":null},{"url":null,"slug":"civil-causal-and-intuitive-visual-imitation","title":"CIVIL: Causal and Intuitive Visual Imitation Learning","date":"2025-04-24","arxiv_id":"2504.17959","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborating-action-by-action-a-multi-agent","title":"Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning","date":"2025-04-24","arxiv_id":"2504.17950","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-learning-based-manipulation-and","title":"Integrating Learning-Based Manipulation and Physics-Based Locomotion for Whole-Body Badminton Robot Control","date":"2025-04-24","arxiv_id":"2504.17771","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":"exposing-the-copycat-problem-of-imitation","title":"Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline","date":"2025-04-20","arxiv_id":"2504.14709","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-based-approach-to-imitation-learning","title":"A Model-Based Approach to Imitation Learning through Multi-Step Predictions","date":"2025-04-18","arxiv_id":"2504.13413","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-with-precisely-labeled","title":"Imitation Learning with Precisely Labeled Human Demonstrations","date":"2025-04-18","arxiv_id":"2504.13803","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossing-the-human-robot-embodiment-gap-with","title":"Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration","date":"2025-04-17","arxiv_id":"2504.12609","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-a-world-model-for-trajectory","title":"Adapting a World Model for Trajectory Following in a 3D Game","date":"2025-04-16","arxiv_id":"2504.12299","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-models-for-robotic-manipulation-a","title":"Diffusion Models for Robotic Manipulation: A Survey","date":"2025-04-11","arxiv_id":"2504.08438","repositories_listed":0,"syntology":null},{"url":null,"slug":"stratified-expert-cloning-with-adaptive","title":"Stratified Expert Cloning with Adaptive Selection for User Retention in Large-Scale Recommender Systems","date":"2025-04-08","arxiv_id":"2504.05628","repositories_listed":0,"syntology":null},{"url":null,"slug":"tool-as-interface-learning-robot-policies","title":"Tool-as-Interface: Learning Robot Policies from Human Tool Usage through Imitation Learning","date":"2025-04-06","arxiv_id":"2504.04612","repositories_listed":0,"syntology":null},{"url":null,"slug":"dexterous-manipulation-through-imitation","title":"Dexterous Manipulation through Imitation Learning: A Survey","date":"2025-04-04","arxiv_id":"2504.03515","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-world-models-coupling-video-and","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","date":"2025-04-03","arxiv_id":"2504.02792","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-lat-bilateral-control-based-imitation","title":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","date":"2025-04-02","arxiv_id":"2504.01301","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-with-imperfect-models-when-multi","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","date":"2025-04-02","arxiv_id":"2504.01766","repositories_listed":0,"syntology":null},{"url":null,"slug":"cbil-collective-behavior-imitation-learning","title":"CBIL: Collective Behavior Imitation Learning for Fish from Real Videos","date":"2025-03-31","arxiv_id":"2504.00234","repositories_listed":0,"syntology":null},{"url":null,"slug":"hacts-a-human-as-copilot-teleoperation-system","title":"HACTS: a Human-As-Copilot Teleoperation System for Robot Learning","date":"2025-03-31","arxiv_id":"2503.24070","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-coordinated-bimanual-manipulation","title":"Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models","date":"2025-03-30","arxiv_id":"2503.23271","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-analysis-of-sim-and-real-cotraining","title":"Empirical Analysis of Sim-and-Real Cotraining Of Diffusion Policies For Planar Pushing from Pixels","date":"2025-03-28","arxiv_id":"2503.22634","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-offline-imitation-learning-through","title":"Robust Offline Imitation Learning Through State-level Trajectory Stitching","date":"2025-03-28","arxiv_id":"2503.22524","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-tokens-a-flexible-approach-to-adapting","title":"Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models","date":"2025-03-28","arxiv_id":"2503.22886","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-imitation-learning-discovering","title":"Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning","date":"2025-03-27","arxiv_id":"2503.21406","repositories_listed":0,"syntology":null},{"url":null,"slug":"ominiadapt-learning-cross-task-invariance-for","title":"OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation","date":"2025-03-27","arxiv_id":"2503.21257","repositories_listed":0,"syntology":null}],"record_sha256":"9678cb49444966f68a2a28c062a1e0de712d348a78ade73b003d551a48ac094d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}