[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.
☆134Mar 31, 2026Updated last week
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:
- Responsible Robotic Manipulation☆15Aug 31, 2025Updated 7 months ago
- A vision-language-safety action architecture, named AEGIS, which contains a plug-and-play safety constraint layer formulated via control …☆79Updated this week
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆32Jun 23, 2025Updated 9 months ago
- [AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks☆43Nov 24, 2025Updated 4 months ago
- Official repo of Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics☆73Mar 26, 2026Updated 2 weeks 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.
- Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning☆18May 16, 2025Updated 10 months ago
- [ICRA 2026] Official implemetation of the paper "InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning"☆48Feb 2, 2026Updated 2 months ago
- ☆21Jul 26, 2025Updated 8 months ago
- Codes for paper "SafeAgentBench: A Benchmark for Safe Task Planning of \\ Embodied LLM Agents"☆68Feb 25, 2025Updated last year
- This is the official repository for "SAFE: Multitask Failure Detection for Vision-Language-Action Models" (NeurIPS 2025)☆64Jan 18, 2026Updated 2 months ago
- Official GitHub repository for the paper "Adversarial Attacks on Robotic Vision Language Action Models"☆31May 28, 2025Updated 10 months ago
- ☆17Sep 25, 2024Updated last year
- Tactile ergodic exploration for robot learning☆14Dec 16, 2024Updated last year
- ☆18May 9, 2023Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆59Jul 21, 2025Updated 8 months ago
- ☆26Mar 11, 2025Updated last year
- [ICRA 2026] 🌠 DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation☆32Jan 14, 2026Updated 2 months ago
- SafeSora is a human preference dataset designed to support safety alignment research in the text-to-video generation field, aiming to enh…☆34Aug 20, 2024Updated last year
- AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation☆39Feb 23, 2026Updated last month
- 【ACL 2024】 SALAD benchmark & MD-Judge☆172Mar 8, 2025Updated last year
- Official PyTorch implementation for NeurIPS 2024 paper: Prediction with Action.☆50Jan 4, 2025Updated last year
- ☆85Feb 12, 2026Updated last month
- Code for FLIP: Flow-Centric Generative Planning for General-Purpose Manipulation Tasks☆82Dec 12, 2024Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Official Code for SGRv2 and SGR.☆33May 20, 2025Updated 10 months ago
- SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World☆152Nov 4, 2024Updated last year
- [ICLR 2026] Official implemetation of the paper "Policy Contrastive Decoding for Robotic Foundation Models"☆26Mar 5, 2026Updated last month
- [ICLR 2025] Official implementation for "SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanati…☆44Feb 11, 2025Updated last year
- [ICRA 25] FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning☆45Jan 5, 2025Updated last year
- Source materials for CoinFT☆30Jan 23, 2026Updated 2 months ago
- StereoVLA is powered by stereo vision and supports flexible deployment with high tolerance to camera pose variations.☆61Jan 12, 2026Updated 2 months ago
- Reimplementation of facebook's DinoV2 in JAX. Inference (with pretrained weights) only; training is unsupported.☆12Jun 25, 2024Updated last year
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success☆1,132Sep 9, 2025Updated 7 months ago
- Official implementation for the LABOR (LAnguage-model-based Bimanual ORchestration) Agent.☆21Nov 23, 2024Updated last year
- Repo for Bring Your Own Vision-Language-Action (VLA) model, arxiv 2024☆37Jan 22, 2025Updated last year
- A Modular interface for robotic manipulation.☆20Nov 20, 2024Updated last year
- Diagnostic Framework for LLMs and MLLMs☆36Mar 2, 2026Updated last month
- Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.☆413Nov 11, 2025Updated 5 months ago
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆1,038Nov 19, 2025Updated 4 months ago