Haoze Sun

X-WAM. Official implemetation of the paper "Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising".

AHA-WAM. AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

UniT. Python

Xangine. Xangine is a 3D graphics and simulation engine by Tesseract Studios.

OpenSpatial. Python

JoyAI-Image. JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

dpdmd. [ICML 2026] The offical code of Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

VST. Visual Spatial Tuning, ECCV2026

VQASynth. Compose multimodal datasets 🎹

Vision-Language-Models-Overview. A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

Project-Xangine-Old. Tesseract Xangine is a game engine by Tesseract Studios based on OpenSceneGraph.

Paper2Poster. [NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

BLIP3o. Official implementation of BLIP3o-Series

AdcSR. (CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]

AFINE. Official code for our CVPR 2025 paper: "Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption"

thuthesis. LaTeX Thesis Template for Tsinghua University

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

GameFactory. [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

FreeScale. [ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation

Embodied_AI_Paper_List. [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.

OmniGen. OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

SiD. PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)

CoSeR. An unofficial implementation for "CoSeR: Bridging Image and Language for Cognitive Super-Resolution (CVPR 2024)"

emoji-cheat-sheet. A markdown version emoji cheat sheet

ControlNeXt. Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

MGM. Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

MLLMs-for-IQA. [ECCV 2024] Official Pytorch Implementation of A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment

SeeSR. [CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

StyleCrafter. [TOG 2024]StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

StableSR. [IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

Assessor360. [NeurIPS 2023] Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment

SSD. [IJCAI 2024] SSD: Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

Awesome-Super-Resolution. Collect super-resolution related papers, data, repositories

HandyView. Handy image viewer based on PyQt5. Convenient for viewing and comparing :-)

SimDeblur. Simple framework for image and video deblurring, implemented by PyTorch

TianheWu.

Awesome-Deblurring. A curated list of resources for Image and Video Deblurring

ECCV2022-Paper-Code-Interpretation. ECCV2022 论文/代码/解读合集，极市团队整理