mlsanityData to 7 Oct 2026

Robot manipulation imitation learning

737 papers11 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: manipulation, imitation, imitation learning, robot, demonstrations

Key facts. Robot manipulation imitation learning: 737 papers on arXiv since 2018 (data through 7 Oct 2026). 140 of its 737 mapped papers (19%) cite “Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware” (2023, arXiv 2304.13705). 45 of its 737 mapped papers (6%) cite “BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning” (2022, arXiv 2202.02005). 28 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

28 new papers, 17 Sep – 7 Oct; 11 this week.

  1. This week · 11
  2. RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input also fits: Real-world robot offline RL
  3. Targeted Modality Dropout for Real-Robot Manipulation Robust to Intermittent Vision Loss
  4. Contact-Aware Imitation Learning Through Contact Factorization
  5. Fast Non-Parametric Heteroscedastic Imitation Learning With Geometric Priors also fits: Robot learning from demonstration
  6. BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation also fits: Real-world robot offline RL
  7. Behavioral Cloning Mystery also fits: Imitation learning methods
  8. Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks
  9. Adaptive Mean Flow for Responsive Closed-Loop Robot Control also fits: Robot learning from demonstration
  10. Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning
  11. Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor Imitation also fits: Imitation learning methods
All 28
  1. Learning Coordinated Visuomotor Box-Pushing from Solo Demonstrations
  2. Earlier · 17
  3. Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation
  4. AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
  5. Memorize, Adapt, Ignore: Diagnosing Robot Learning Mechanisms under Training Data Variation also fits: Language-conditioned policies and VLAs
  6. BlenDAgger: Blended Shared Control for Interactive Imitation Learning
  7. Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control
  8. Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning also fits: Imitation learning methods
  9. From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations
  10. HOI-Retarget: Contact-Centric Retargeting for Human-Object Interaction also fits: Real-world robot offline RL
  11. An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning
  12. Enabling a Unified Cross-Domain Representation for Two-Finger Gripper Manipulation via Interaction-Centric Modeling
  13. POIL: Point-based One-Shot Imitation Learning with Stable Dynamical Systems
  14. Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation also fits: Real-world robot offline RL
  15. Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning
  16. EgoSpeedUp: Transferring Human Manipulation Tempo to Robot Policies
  17. Learning from Mixed-Quality Deployment Experience for Robot Manipulation also fits: Real-world robot offline RL
  18. The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models also fits: Imitation learning methods
  19. BEACON: Belief-Enabled Adaptive CONtrol for Imitation Learning under Uncertainty

Foundations

Most cited by papers here

  1. Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023cited by 140 here
  2. BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning2022cited by 45 here
  3. Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation2024cited by 37 here
  4. MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations2023cited by 35 here
  5. Behavior Transformers: Cloning k modes with one stone2022cited by 33 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2018An Algorithmic Perspective on Imitation Learningcited by 57 here
  2. 2021Implicit Behavioral Cloningcited by 52 here
  3. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 25 here
  4. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 21 here
20 more it builds on, not in this chain
  1. 2018Behavioral Cloning from Observationcited by 24 here
  2. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 31 here
  3. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 24 here
  4. 2019Self-Supervised Correspondence in Visuomotor Policy Learningcited by 22 here
  5. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 20 here
  6. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrationscited by 24 here
  7. 2020Visual Imitation Made Easycited by 30 here
  8. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 22 here
  9. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 90 here
  10. 2021The Surprising Effectiveness of Representation Learning for Visual Imitationcited by 23 here
  11. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 45 here
  12. 2022Behavior Transformers: Cloning k modes with one stonecited by 33 here
  13. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 28 here
  14. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 140 here
  15. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 24 here
  16. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 19 here
  17. 2023GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulatorscited by 25 here
  18. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 35 here
  19. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 37 here
  20. 2024ALOHA Unleashed: A Simple Recipe for Robot Dexteritycited by 20 here

The 24 most cited of 635.

Browse

30 of 737, ranked 6–35

  1. 6Visual Imitation Made Easy202030
  2. 7VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors202228
  3. 8MimicPlay: Long-Horizon Imitation Learning by Watching Human Play202325
  4. 9GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators202325
  5. 10BridgeData V2: A Dataset for Robot Learning at Scale202324
  6. 11Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations202024
  7. 12RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation201824
  8. 13The Surprising Effectiveness of Representation Learning for Visual Imitation202123
  9. 14Human-in-the-Loop Imitation Learning using Remote Teleoperation202022
  10. 15Self-Supervised Correspondence in Visuomotor Policy Learning201922
All 30
  1. 16Data Scaling Laws in Imitation Learning for Robotic Manipulation202421
  2. 17ALOHA Unleashed: A Simple Recipe for Robot Dexterity202420
  3. 18Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning201920
  4. 19Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics202418
  5. 20DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation202417
  6. 21Open-TeleVision: Teleoperation with Immersive Active Visual Feedback202417
  7. 22VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training202217
  8. 23Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration202117
  9. 24Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation202117
  10. 25Data Quality in Imitation Learning202316
  11. 26Waypoint-Based Imitation Learning for Robotic Manipulation202314
  12. 273D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations202413
  13. 28In-Context Imitation Learning via Next-Token Prediction202413
  14. 29Instant Policy: In-Context Imitation Learning via Graph Diffusion202413
  15. 30Learning and Retrieval from Prior Data for Skill-based Imitation Learning202213
  16. 31DexMV: Imitation Learning for Dexterous Manipulation from Human Videos202113
  17. 32Imitation Learning Based on Bilateral Control for Human-Robot Cooperation201913
  18. 33Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation202312
  19. 34Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning202212
  20. 35Reinforcement and Imitation Learning for Diverse Visuomotor Skills201812