Starred repositories
Official Implementation of VisualClaw: A Real-Time, Personalized Agent for the Physical World
[ICML 2026] Official implementation of Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
Official repository for Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
[AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
[TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…
Fully open reproduction of DeepSeek-R1
[TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
Universal and Transferable Attacks on Aligned Language Models