Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

RoboTwin 2.0 Offical Repo

[ICRA 2026] VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

Official PyTorch implementation of Deformable Grid (ECCV 2020)

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

EvoVLA: Self-Evolving Vision-Language-Action Model

[AAAI'26 Oral] DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

[NeurIPS 2025] VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulation

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

PyTorch and TensorFlow implementation of NCP, LTC, and CfC wired neural models

Code Repository for Liquid Time-Constant Networks (LTCs)

Training ImageNet / CIFAR models with sota strategies and fancy techniques such as ViT, KD, Rep, etc.

Real-Time VLAs via Future-state-aware Asynchronous Inference.

RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation

RynnVLA-002: A Unified Vision-Language-Action and World Model

[ICRA 2026] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

This repository contains the official implementation of "FlowIE: Efficient Image Enhancement via Rectified Flow"

(TPAMI' 25) Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

A Paper List for Humanoid Robot Learning.

[NeurIPS2024] Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

🦾 A Dual-System VLA with System2 Thinking

[ICCV 2023] Official implementation of "Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding" in International Conference on Computer Vision (ICCV) 2023.

Official implementation of our NeurIPS 2025 paper: "FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts."

Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

The inference module for AgiBot X1.

The reinforcement learning training code for AgiBot X1.

This repository implements teleoperation of the Unitree humanoid robot using XR Devices.