PKU-Alignment / SafeVLALinks
[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.
☆90Updated 2 weeks ago
Alternatives and similar repositories for SafeVLA
Users that are interested in SafeVLA are comparing it to the libraries listed below
Sorting:
- Responsible Robotic Manipulation☆15Updated 3 months ago
- GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization☆153Updated 8 months ago
- [ICCV 2025] RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints☆97Updated 3 months ago
- [ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.☆236Updated 2 months ago
- Official code for the paper: Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld☆60Updated last year
- Code for Reinforcement Learning from Vision Language Foundation Model Feedback☆133Updated last year
- Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.☆344Updated last month
- LIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark☆128Updated this week
- ☆213Updated 3 months ago
- Official repository of LIBERO-plus, a generalized benchmark for in-depth robustness analysis of vision-language-action models.☆144Updated this week
- [ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"☆82Updated 6 months ago
- ICCV2025☆146Updated last week
- Interactive Post-Training for Vision-Language-Action Models☆156Updated 6 months ago
- Official Implementation of FLARE (AAAI'25 Oral)☆27Updated 3 weeks ago
- HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model☆325Updated 2 months ago
- 🦾 A Dual-System VLA with System2 Thinking☆123Updated 4 months ago
- Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.☆365Updated last month
- Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"☆203Updated 6 months ago
- [NeurIPS 2025] VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning☆64Updated 2 months ago
- InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation☆83Updated 2 months ago
- Official implementation of the paper: Task Reconstruction and Extrapolation for $\pi_0$ using Text Latent (https://arxiv.org/pdf/2505.035…☆94Updated 4 months ago
- Official Implementation of ReALFRED (ECCV'24)☆44Updated last year
- Code for FLIP: Flow-Centric Generative Planning for General-Purpose Manipulation Tasks☆79Updated last year
- [NeurIPS 2024] CLOVER: Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation☆130Updated 3 months ago
- https://arxiv.org/pdf/2506.06677☆40Updated last month
- Official code of paper "DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution"☆120Updated 10 months ago
- Official implementation of Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation. Accepted in NeurIPS 2025.☆87Updated last week
- ☆89Updated last year
- An example RLDS dataset builder for X-embodiment dataset conversion.☆52Updated 9 months ago
- [ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos☆152Updated 2 months ago