🌎💪 BrowserGym, a Gym environment for web task automation

A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architectures

[NeurIPS 2025🔥]Main source code of SRPO framework.

ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).

A version of verl to support diverse tool use

Think Beyond Images

My learning notes/codes for ML SYS.

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

Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

Scaling RL on advanced reasoning models

[ICLR 2025] The First Multimodal Seach Engine Pipeline and Benchmark for LMMs

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning

[ICML 2025🔥] ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

健康学习到150岁 - 人体系统调优不完全指南

Learning Safety Constraints for Large Language Models (ICML2025)

MiMo-VL

Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"

[NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis

Citysub: Controlling Bounds

Official PyTorch implementation of EMOVA in CVPR 2025 (https://arxiv.org/abs/2409.18042)