Starred repositories
Build and install Paddle Inference GPU 3. from source on NVIDIA Jetson (JetPack 6.x, CUDA 12), with TensorRT support and known issue fixes.
10
Updated Jan 26, 2026
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
Synthetic data curation for post-training and structured data extraction
An open-source AI agent that brings the power of Gemini directly into your terminal.
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"
A curated list of Multi-Modal Reinforcement Learning resources (continually updated)
A curated collection of papers on Vision-Language Models for Image Understanding from CVPR 2025
6
Updated Jun 9, 2025
Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.
Movie Gen Bench - two media generation evaluation benchmarks released with Meta Movie Gen
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
This is the Repository for Geometry Problem Solving Method Evaluation
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
The development and future prospects of large multimodal reasoning models.
[NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example
verl: Volcano Engine Reinforcement Learning for LLMs
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
A curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications.