Official PyTorch Implementation of "Flow Map Distillation Without Data"

[ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

Autonomous GPU Kernel Generation via Deep Agents

Native Multimodal Models are World Learners

MrlX: A Multi-Agent Reinforcement Learning Framework

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

StreamingVLM: Real-Time Understanding for Infinite Video Streams

The official implementation of paper “VChain: Chain-of-Visual-Thought for Reasoning in Video Generation”

Papers and implementations of distillation for diffusion models

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

🗂 The perfect Front-End Checklist for modern websites and meticulous developers

Puzzles for learning Triton

This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".

Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache

Generate image at any resolution.

💥 Blazing fast terminal file manager written in Rust, based on async I/O.

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures

Reference PyTorch implementation and models for DINOv3

OpenVLA: An open-source vision-language-action model for robotic manipulation.

A Large-Scale Computation Graph Database for Tensor Compiler Research

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Unified Multimodal Model for image generation/editing/understanding

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

The source of LMSYS website and blogs

slime is an LLM post-training framework for RL Scaling.