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

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

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

[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

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

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

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.

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

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

A metrics library to evaluate vision language models with a pytorch eco system.

CS7675: Benchmarking robot learning algorithms for real-world challenges (Master's Research)

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

A repository for my master thesis within Solving Dynamic and Stochastic Manipulation tasks with Human Teleoperation and different Imitation Learning methods.

The official implementation of Dichotomous Diffusion Policy Optimization (DIPOLE) in RL bench