Stars
[RSS 2026] Causal video-action world model for generalist robot control
[ICLR 2026] Efficient Agent Training for Computer Use
Use DINOv3’s powerful, self-supervised visual features + YOLOv12’s blazing-fast detection, all in one repo. Whether you have only a few hundred labeled images or a medium-sized dataset, DINOV3-YOLO…
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency
Helios: Real Real-Time Long Video Generation Model
[CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction
[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO
MS-Agent: a lightweight framework to empower agentic execution of complex tasks
The official project website of "Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models" (CoM-PT for short, accepted to CVPR 2026)
A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.
Official PyTorch implementation of GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers (NeurIPS 2025)
[ICLR 2026] StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
HY-Embodied: Embodied Foundation Models for Real-World Agents
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)
Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
[NeurIPS 2025] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
AI agents running research on single-GPU nanochat training automatically
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).
PyTorch code and models for VJEPA2 self-supervised learning from video.
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…