Opdoop
Follow
Stars
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767
A lightweight, powerful framework for multi-agent workflows
Train your AI self, amplify you, bridge the world
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
CodeScientist: An automated scientific discovery system for code-based experiments
The official repository for the Scientific Paper Idea Proposer (SciPIP)
ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory
SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing
DeepLiterature: A fully open-source intelligent research assistant that integrates search, code execution, link resolution, and information expansion, with multiple tools working together to facili…
The official GitHub page for the survey paper "A Survey of Large Language Models".
zero-shot voice conversion & singing voice conversion, with real-time support
From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems
最好用的 sing-box 一键安装脚本 & 管理脚本，自动创建 REALITY 协议；支持 TUIC，Trojan，Hysteria2 等所有常见的协议
An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions.…
DeepEP: an efficient expert-parallel communication library
Repo for paper: Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge
Making large AI models cheaper, faster and more accessible
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
Safety at Scale: A Comprehensive Survey of Large Model Safety
Improving Math reasoning through Direct Preference Optimization with Verifiable Pairs
Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥
Dromedary: towards helpful, ethical and reliable LLMs.
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal