Stars
PrivacyGuard platform for Privacy Attacks and Analysis. Perform privacy analyses of ML models using Inference Attacks and Extraction Attacks. PrivacyGuard library implements varied, SotA privacy at…
Train your Agent model via our easy and efficient framework
Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
LeetCode Training and Evaluation Dataset
A database operations and data analysis AI agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
程序员延寿指南 | A programmer's guide to live longer
[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
A final sanity checklist to help your CS paper get accepted, not desk rejected.
A family of open-sourced Mixture-of-Experts (MoE) Large Language Models
基于小红书 Web 端进行的请求封装。https://reajason.github.io/xhs/
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.
End-to-end codebase for finetuning LLMs (LLaMA 2, 3, etc.) with or without DP
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Building a comprehensive and handy list of papers for GUI agents
[ICLR 2025] Dissecting adversarial robustness of multimodal language model agents
[ICML 2024] TrustLLM: Trustworthiness in Large Language Models
Minimal reproduction of DeepSeek R1-Zero
SGLang is a fast serving framework for large language models and vision language models.
A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Fully open reproduction of DeepSeek-R1
Recommend new arxiv papers of your interest daily according to your Zotero libarary.