个人构建MoE大模型：从预训练到DPO的完整实践

A modern, open-source, self-hosted knowledge management and note-taking platform designed for privacy-conscious users and organizations.

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

《剑指 Offer》 Python, Java, C++ 解题代码，LeetBook《图解算法数据结构》配套代码仓

Build Real-Time Knowledge Graphs for AI Agents

An open protocol enabling communication and interoperability between opaque agentic applications.

Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI

[TIFS 2024] Natias: Neuron Attribution based Transferable Image Adversarial Steganography