SGLang is a high-performance serving framework for large language models and multimodal models.

[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filli…

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

Code For EMNLP 2025: Test-Time Steering for Lossless Text Compression via Weighted Product of Experts

PAI-Bench: A Comprehensive Benchmark for Physical AI

Paper reading notes on Deep Learning and Machine Learning

AGENTS.md — a simple, open format for guiding coding agents

SLURM Installer

The official implementation of NeurIPS 2025 paper named "RetroSynFlow: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis".

The official implementation of 'Equivariant Denoisers Cannot Copy Graphs: Aligned your Graph Diffusion Models' (ICLR2025)

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics

Official Repo for Self-Forcing++ High Quality Long Video Generation

LongLive: Real-time Interactive Long Video Generation

[Preprint] UCGM: Unified Continuous Generative Models

[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"

VS Code in the browser

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

Pytorch implementation for MeanFlow

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Transition Models

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

💡 VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. This specific repository is geared towards integration with eventual Alphafold2 replication.

[ECCV 2022] Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction

Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]