bdaiinstitute / theiaLinks
Theia: Distilling Diverse Vision Foundation Models for Robot Learning
☆252Updated 5 months ago
Alternatives and similar repositories for theia
Users that are interested in theia are comparing it to the libraries listed below
Sorting:
- [ICML 2025] OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction☆105Updated 5 months ago
- A Vision-Language Model for Spatial Affordance Prediction in Robotics☆191Updated 2 months ago
- [ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy☆224Updated 5 months ago
- Official Repository for SAM2Act☆159Updated last month
- Official Repository for MolmoAct☆193Updated 2 weeks ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆267Updated 2 months ago
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆260Updated 6 months ago
- ☆270Updated 6 months ago
- Code for subgoal synthesis via image editing☆142Updated last year
- [CoRL2024] Official repo of `A3VLM: Actionable Articulation-Aware Vision Language Model`☆119Updated 11 months ago
- Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets☆127Updated last week
- Official codebase for "Any-point Trajectory Modeling for Policy Learning"☆247Updated 3 months ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆375Updated 8 months ago
- [RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre…☆152Updated 11 months ago
- [ICRA 2025] In-Context Imitation Learning via Next-Token Prediction☆93Updated 6 months ago
- ☆55Updated 9 months ago
- Unified Vision-Language-Action Model☆193Updated 2 months ago
- ☆56Updated 8 months ago
- ICCV2025☆133Updated last month
- VLAC: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning☆142Updated this week
- Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"☆279Updated last year
- Embodied Reasoning Question Answer (ERQA) Benchmark☆212Updated 6 months ago
- ☆266Updated last year
- ☆102Updated 2 weeks ago
- Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos☆154Updated 3 weeks ago
- A unified architecture for multimodal multi-task robotic policy learning.☆163Updated last year
- ☆122Updated 2 years ago
- A Benchmark for Evaluating Generalization for Robotic Manipulation☆137Updated 6 months ago
- Official repository of Learning to Act from Actionless Videos through Dense Correspondences.☆229Updated last year
- Autoregressive Policy for Robot Learning (RA-L 2025)☆139Updated 6 months ago