JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

Code repo for FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs.

OS-Sentinel

Sparser Block-Sparse Attention via Token Permutation

Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

A list of recent papers about Link Prediction.

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

Fast and memory-efficient exact attention

A version of verl to support diverse tool use

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

The absolute trainer to light up AI agents.

Awesome List for Agentic RL

WideSearch: Benchmarking Agentic Broad Info-Seeking

Official Repository of "Learning what reinforcement learning can't"

A very simple GRPO implement for reproducing r1-like LLM thinking.

Atom of Thoughts (AoT) MCP is a server that decomposes complex problems into independent atomic units of thought, using the dependencies between these units to deliver more robust reasoning and val…

[NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling

Code for "From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios"

An open-source AI agent that brings the power of Gemini directly into your terminal.

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Democratizing Reinforcement Learning for LLMs

Extract information from various climate scientific graphics to combat misinformation and support scientific communication

An Arena-style Automated Evaluation Benchmark for Detailed Captioning

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