Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Official code of RDT 2

Fully Open Framework for Democratized Multimodal Training

Solve puzzles. Improve your pytorch.

[CoRL 2025] ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training

Code for the paper "3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation"

Official code for "Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation"

Official Repository for MolmoAct

[NeurIPS 2025] Official implementation of "RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics"

[arXiv 2025] CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation

A simulation evaluation platform for DROID

[CoRL 2025] Pretraining code for FLOWER VLA on OXE

PyTorch code and models for VJEPA2 self-supervised learning from video.

RoboBrain 2.0: Advanced version of RoboBrain. See Better. Think Harder. Do Smarter. 🎉🎉🎉

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

PyTorch implementation of Shortcut Models [Frans, 2025] with little modification

MAGI-1: Autoregressive Video Generation at Scale

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

[CoRL 25] Code for FLOWER VLA for finetuning FLOWER on CALVIN and all LIBERO environments

Inference script for Oasis 500M

(CVPR 2025) A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

[CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

X-IL: Exploring the Design Space of Imitation Learning Policies

Wan: Open and Advanced Large-Scale Video Generative Models