A unified inference and post-training framework for accelerated video generation.

Enjoy the magic of Diffusion models!

This is the official repo of MMVP: motion-matrix-based video prediction (ICCV 2023)

Open-Sora: Democratizing Efficient Video Production for All

Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

A simple, easy-to-hack GraphRAG implementation

This is the project for the paper at ICCV 2025

LongLive: Real-time Interactive Long Video Generation

This is a pytorch project for the paper Universal Adaptive Data Augmentation (IJCAI2023).

The code for TPAMI paper "Text-Guided Human Image Manipulation via Image-Text Shared Space"

The source code of Paper "Push the Limit of Scene Text Recognition Using Character and Text Length Guided Text Super-resolution"

This is the source code for CVPR paper "Low-Light Image Enhancement via Structure Modeling and Guidance"

An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

My Pages

[CVPR 2024] Official Code for the Paper "Compositional Chain-of-Thought Prompting for Large Multimodal Models"

Awesome papers involving LLMs in Social Science.

[ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"

Awesome Unified Multimodal Models

[CVPR 2025 Highlight] Official Implementation of SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity

西工大计算机专业课程攻略 | npu-cs/Course-Material

[NeurIPS 2024] Official Implementation of Hawk: Learning to Understand Open-World Video Anomalies

CVPR2025

[ICRA2023] Efficient Implicit Neural Reconstruction Using LiDAR

📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

[ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓