Stars
LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
[RSS'26] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.
Official implementation of FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer
[CVPR 2026] HiF-VLA: An efficient, bidirectional spatiotemporal expansion Vision-Language-Action Model
[NeurIPS 2025] Implementation of the paper "BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent"
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
WoW (World-Omniscient World Model) is a generative world model trained on 2 million robotic interaction trajectories, designed to imagine, reason, and act in the physical world. Unlike passive vide…
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
Official implementation of our serial spatial intelligence robotc foundation model (SLA & Spatial Forcing[ICLR2026]).
Zxy-MLlab / LIBERO-PRO
Forked from Lifelong-Robot-Learning/LIBEROLIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark
VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning
Official implementation of TrajBooster
[ICCV 2025] Implementation of the paper "Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs"
[ICLR 2026] RecA: visual understanding help generation through self-supervised learning
[NeurIPS 2025] VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
[ECCV 2026] Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.
LLaVA-VLA: A Simple Yet Powerful Vision-Language-Action Model [ICRA 2026]
PyTorch code and models for VJEPA2 self-supervised learning from video.
Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning
This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.
VR-based Robot Teleoperation and Data Collection System for Humanoid Whole-Body VLA (Unitree G1)
A paper list for spatial reasoning
[ICLR 2026] MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, realistic, and adaptive scene generation for app…
[NeurIPS 2025 Spotlight] SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation