Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
MiniMax-M2, a model built for Max coding & agentic workflows.
AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling
rCM: SOTA Diffusion Distillation & Few-Step Video Generation
Post-training with Tinker
Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
Building General-Purpose Robots Based on Embodied Foundation Model
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion models are significantly more data-efficient than standard left…