AgentFlow: In-the-Flow Agentic System Optimization

My learning notes/codes for ML SYS.

Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay

Democratizing Reinforcement Learning for LLMs

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Train transformer language models with reinforcement learning.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Building a comprehensive and handy list of papers for GUI agents

This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

A Survey of Reinforcement Learning for Large Reasoning Models

Collect every awesome work about r1!

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

verl: Volcano Engine Reinforcement Learning for LLMs

Open-source unified multimodal model

AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

Implementation for "The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer"

Fully open reproduction of DeepSeek-R1

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

A framework for few-shot evaluation of language models.

A collection of benchmarks and datasets for evaluating LLM.

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…

Code for [CVPR 2025] ROICtrl: Boosting Instance Control for Visual Generation

[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

Awesome LLMs on Device: A Comprehensive Survey

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

Out-of-the-box (OOTB) GUI Agent for Windows and macOS