Galaxea's first VLA release

Official code of RDT 2

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

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

Code for RSS 2025 paper "Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies"

Visual Imitation Enables Contextual Humanoid Control. arXiV, 2025.

Cameras as Relative Positional Encoding

[CoRL 2025] RISE-2: A Generalizable Imitation Learning Policy

[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation

🦾 A Dual-System VLA with System2 Thinking

[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation

Universal Monocular Metric Depth Estimation

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

Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

Attention mappers and visualisation for transformer-based Physical AI policies

[ICLR 25] Code for "Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning"

[ICRA 25] FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning

✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints