15k open math problems, linked to their sources.

Code for the paper Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

Toolathlon-Gym for testing AI agents real-world tool-use capabilities across diverse MCP servers.

Stable Looped Models and their Scaling Laws

Official Implementation of "Maximum Likelihood Reinforcement Learning (MaxRL)"

Official JAX implementation of End-to-End Test-Time Training for Long Context

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Data recipes and robust infrastructure for training AI agents

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

Graph SLAM을 하기 위한 Ceres tutorial 코드들

An Invitation to 3D Vision: A Tutorial for Everyone

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Experiment with diffusion models that you can run on your local jupyter instances

Generates random simple polygons.

Auditing agents for fine-tuning safety

Anchored Diffusion Language Model (NeurIPS 2025)

📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

A Sober Look at Language Model Reasoning

Pretraining and inference code for a large-scale depth-recurrent language model

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models