Starred repositories
Building a comprehensive and handy list of papers for GUI agents
A Next-Generation Training Engine Built for Ultra-Large MoE Models
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Mobile-Agent: The Powerful GUI Agent Family
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
slime is an LLM post-training framework for RL Scaling.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Autonomous Agents (LLMs) research papers. Updated Daily.
[ICML 2025] SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
Easily train a good VC model with voice data <= 10 mins!
The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment
an extremely simple tool for separating vocals and background music, completely localized for web operation, using 2stems/4stems/5stems models 这是一个极简的人声和背景音乐分离工具，本地化网页操作，无需连接外网
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.
Official repo of Griffon series including v1(ECCV 2024), v2(ICCV 2025), G, and R, and also the RL tool Vision-R1.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.
Explore the Multimodal “Aha Moment” on 2B Model
[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
[ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
Collect every awesome work about r1!
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning