Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
- adversarial-attacks
- ai-safety
- autonomous-driving
- backdoor-attacks
47,133 repositories indexed
97–108 of 108 · Most stars
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.
AFI VISION BUILDER
Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agentic development.
A Tensorfflow implementation of Attend, Infer, Repeat
An Easy To Use PyTorch Computer Vision Library
A foundation model-driven whole slide image-scale cell phenotyping method with QuPath integration Resources
Python Target Tracking for 2019 FRC Season
👀 Powerful vision code for FRC
YOLOv5 - most advanced vision AI model for object detection. Natively implemented in PyTorch and exportable to TFLite for use in edge solutions.
:briefcase: An ansible role to provision physical and virtual hosts with the AWS SSM agent.