OpenDriveLab / UniVLALinks
[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions
β446Updated this week
Alternatives and similar repositories for UniVLA
Users that are interested in UniVLA are comparing it to the libraries listed below
Sorting:
- π₯ SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.β360Updated this week
- β362Updated 5 months ago
- HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelβ239Updated last week
- DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Graspingβ283Updated last week
- A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationβ288Updated 3 weeks ago
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successβ481Updated last month
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.ioβ207Updated last month
- Embodied Chain of Thought: A robotic policy that reason to solve the task.β267Updated 2 months ago
- Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"β261Updated last year
- [CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"β177Updated 3 months ago
- OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulationβ200Updated 2 weeks ago
- [Actively Maintainedπ₯] A list of Embodied AI papers accepted by top conferences papers (ICLR, NeurIPS, ICML, RSS, CoRL, ICRA, IROS, CVPRβ¦β314Updated 3 weeks ago
- β207Updated 2 months ago
- β147Updated 3 months ago
- Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.β236Updated 2 weeks ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videosβ307Updated 5 months ago
- [ICLR 2025 Oral] Seer: Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationβ191Updated last week
- OpenVLA: An open-source vision-language-action model for robotic manipulation.β213Updated 3 months ago
- [ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Modelβ531Updated 7 months ago
- Official implementation of "Data Scaling Laws in Imitation Learning for Robotic Manipulation"β173Updated 7 months ago
- π A collection of utilities and tools for LeRobot.β249Updated this week
- [CVPR 2025]Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulationβ146Updated this week
- Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.β127Updated last month
- Official codebase for "Any-point Trajectory Modeling for Policy Learning"β225Updated this week
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)β215Updated 3 months ago
- [RSS25] Official implementation of DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learningβ166Updated 2 months ago
- Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"β324Updated 10 months ago
- GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Dataβ126Updated last month
- Latest Advances on Vison-Language-Action Models.β74Updated 3 months ago
- GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimizationβ130Updated 2 months ago