🎨 把时间还给逻辑，用 AI 绘就你的科研故事

A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic

Official code for "Self-Distilled Agentic Reinforcement Learning"

Implementation for representation steering with Concept Distributed Alignment Search (CDAS) (accepted by ICLR 2026).

[ICLR'26] Beyond Linear Probes: Dynamic Safety Monitoring for Language Models

Safety guardrails for LLM-enabled robots

Elevate your AI research writing, no more tedious polishing ✨

骂了么

The official repository for paper: RoboTrust: Evaluating the Interaction Trustworthiness of Multi-modal Large Language Models in Embodied Agents

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System

The code repo of paper "HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task"

Python package for importing and loading external assets into AI2THOR

Awesome World Model for Robotics Papers

This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL

Official implementation for “SafePred: A Predictive Guardrail for Computer-Using Agents via World Models”

[NeurIPS 2025 Spotlight] Official repository for "Web-Shepherd: Advancing PRMs for Reinforcing Web Agents"

Paper List of Inference/Test Time Scaling/Computing

[ICML 2025] World Model Implanting for Test-time Adaptation of Embodied Agents

Advanced Embodied Intelligence Brain Model

[ACL 2025] "World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning." https://arxiv.org/abs/2503.10480

Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"

Implementation of VLM4VLA

📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.