[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.
☆163Mar 31, 2026Updated 6 months ago
Alternatives and similar repositories for SafeVLA
Users that are interested in SafeVLA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A vision-language-safety action architecture, named AEGIS, which contains a plug-and-play safety constraint layer formulated via control …☆139Oct 18, 2026Updated last week
- This is the official repository for "SAFE: Multitask Failure Detection for Vision-Language-Action Models" (NeurIPS 2025)☆111Updated this week
- Responsible Robotic Manipulation☆17Aug 31, 2025Updated last year
- Codes for paper "SafeAgentBench: A Benchmark for Safe Task Planning of \\ Embodied LLM Agents"☆79Feb 25, 2025Updated last year
- Official repo of Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics☆86Mar 26, 2026Updated 7 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆37Jun 23, 2025Updated last year
- The official repository for paper: BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization☆57Dec 9, 2025Updated 10 months ago
- Official GitHub repository for the paper "Adversarial Attacks on Robotic Vision Language Action Models"☆35May 28, 2025Updated last year
- 🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.☆734Jun 23, 2025Updated last year
- ☆27Mar 11, 2025Updated last year
- VLA-Arena is an open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models.☆220Jul 5, 2026Updated 3 months ago
- Repo for Bring Your Own Vision-Language-Action (VLA) model, arxiv 2024☆40Jan 22, 2025Updated last year
- Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.☆465Nov 8, 2025Updated 11 months ago
- [ICLR 2026] Official implemetation of the paper "Policy Contrastive Decoding for Robotic Foundation Models"☆29Sep 3, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [Arxiv] Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms☆149Aug 27, 2026Updated 2 months ago
- HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model☆359Oct 3, 2025Updated last year
- [ICRA 2026] Official implemetation of the paper "InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning"☆51Sep 3, 2026Updated last month
- [ECCV 2026] The code repo of paper "HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task"☆15Jun 21, 2026Updated 4 months ago
- [ICRA 25] FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning☆50Jan 5, 2025Updated last year
- Code for RSS 2025 paper "Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning …☆58Jun 18, 2025Updated last year
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success☆1,438Sep 9, 2025Updated last year
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆29Jun 11, 2025Updated last year
- ☆10Jan 18, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆1,141Nov 19, 2025Updated 11 months ago
- ☆23Jul 26, 2025Updated last year
- A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation☆77Apr 1, 2025Updated last year
- optimization-based latent safety filtering for hard-to-model failures☆16Apr 19, 2026Updated 6 months ago
- Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning☆19May 16, 2025Updated last year
- NeurIPS 2026: Mechanistic Interpretability toolkit for Vision-Language-Action models☆33Oct 1, 2026Updated 3 weeks ago
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆7,231Mar 23, 2025Updated last year
- SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World☆158Nov 4, 2024Updated last year
- AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models☆14Jun 2, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆62Jul 21, 2025Updated last year
- This is the official repository for the ICLR 2025 accepted paper Badrobot: Manipulating Embodied LLMs in the Physical World.☆49Jun 11, 2026Updated 4 months ago
- [ICLR 2026] Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"☆369Jun 13, 2026Updated 4 months ago
- [IROS 2025] ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis☆26May 17, 2025Updated last year
- Backdoor training and evaluation scripts for vision-language-action models on LIBERO.☆12Jul 25, 2026Updated 3 months ago
- ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models☆114Apr 8, 2024Updated 2 years ago
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic Sys…☆158Oct 21, 2026Updated last week