A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

[ICLR 2026] ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

ABC: Scalable Behavior Cloning with Open Data, Training, and Evaluation

Python library for solving reinforcement learning (RL) problems using generative models (e.g. Diffusion Models).

Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

[RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre-trained weights

[CoRL 24] GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy

[CVPR 25] G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation

[ICRA'24] Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning

[AAAI 2026] D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss.

MinBC - Minimal Behavior Cloning

Safe Model Predictive Diffusion: Training-free diffusion planner for provably safe and kinodynamically feasible trajectory

Unofficial implementation of "Generative Modeling via Drifting" on PushT, built on Diffusion Policy

[CVPR'2025] "DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation"

Gym environments for manipulators based on crisp_py and ROS2: collect data and deploy policies on real ROS2 enabled manipulators.

A complete imitation learning pipeline for bar alignment using the UR5 robot in NVIDIA Isaac Sim. Includes manual data collection with a game controller, dataset organization for LeRobot, diffusion policy training, and policy deployment through ROS2.

TacImag: Imagining the Sense of Touch for Robotic Manipulation

Policy-Lightning is a PyTorch Lightning-based implementation of GauDP, DP, DP3, etc.

A curated list of Universal Manipulation Interface (UMI) and UMI-style papers, datasets, code, and hardware for robot-free manipulation demonstrations and robot policy learning.

[ICML 2026] Energy-based Compositional Diffusion Planning