Zhihao Chen

Peak-End-Net. [ACM MM 2026] Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment

wolfcha. AI-powered Werewolf (Mafia) social deduction game where every player is controlled by top LLMs like DeepSeek, Qwen, Gemini, and more

ADE-CoT. [CVPR 26] From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

BlockPilot. Python

DreamX-World. DreamX-World: A General-Purpose Interactive World Model

APPO. Python

roleagent. Python

UniMRG. [ICML 2026] The official implementation of paper "Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation"

TransitLM. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

MACE-Dance. [SIGGRAPH 2026] MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

LLaTiSA. This is the official repository of "LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics".

EMF. [2026 CVPR]Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

DCW. [CVPR 2026] Elucidating the SNR-t Bias of Diffusion Probabilistic Models

FASA-ICLR2026. [ICLR 2026] FASA: FREQUENCY-AWARE SPARSE ATTENTION

AR-MAP-Main. Python

Pos2Distill-. [EMNLP25] Official code for "POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation"

HS-STaR. [EMNLP’ 25] Official code for "HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation"

LD-RPS. [ICCV25] LD-RPS

UPRE-ICCV2025. [ICCV2025] UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement

SkillClaw. Let Skills Evolve Collectively with Agentic Evolver

Omni-WorldBench. A comprehensive benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings.

MobilityBench. [KDD 2026 Oral] MobilityBench: A Scalable Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

Code2World. Code2World: A GUI World Model via Renderable Code Generation

Q-Hawkeye. Python

SpatialGenEval. [ICLR2026] Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

MathForge. [ICLR 2026] Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

SocioReasoner. [ICLR26] Official implementation of the paper "Urban Socio-Semantic Segmentation with Vision-Language Reasoning"

Thinking-with-Map. [ACL 2026 Findings] Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Taming-Hallucinations. JavaScript

BenchX. BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

IC-Light. More relighting!

x-flux. Python

guided-diffusion. Python

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

prompt-to-prompt. Jupyter Notebook

MMN-VSOD. Python

lang-segment-anything. SAM with text prompt

mamba. Mamba SSM architecture

MedKLIP. The official code for MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology. We propose to leverage medical specific knowledge enhancing language-image pre-training method, significantly advancing the ability of pre-trained models to handle unseen diseases on zero-shot classification and grounding tasks.

chexpert-labeler. CheXpert NLP tool to extract observations from radiology reports.

meru. Code for the paper "Hyperbolic Image-Text Representations", Desai et al, ICML 2023

MedRPG. Python

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

vgtr. [ICME'22] Visual Grounding with Transformers

R2Gen. Python

TBraTS. 【MICCAI 2022】"TBraTS: Trusted Brain Tumor Segmentation"

FDRNet. Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"

mmsegmentation. OpenMMLab Semantic Segmentation Toolbox and Benchmark.

BasicSR. Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

SID. Official implementation for ICCV19 "Shadow Removal via Shadow Image Decomposition"

exposure-fusion-shadow-removal. We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.

Implicit-Internal-Video-Inpainting. [ICCV 2021]: IIVI: Internal Video Inpainting by Implicit Long-range Propagation

pytorch-toolbelt. PyTorch extensions for fast R&D prototyping and Kaggle farming

rvos. RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

ViSha. Code for the CVPR 2021 paper "Triple-cooperative Video Shadow Detection"

STM-Training. training script for space time memory network

FEELVOS. FEELVOS implementation in PyTorch; FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

MedicalNet. Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

DEXTR-PyTorch. Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr

Awesome-Crowd-Counting. Awesome Crowd Counting

Mask-ShadowGAN. Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data | ICCV 2019

tutorials. MONAI Tutorials

GridDehazeNet. This repo contains the official training and testing codes for our paper: GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing.

R3Net. Code for the IJCAI 2018 paper "R^3Net: Recurrent Residual Refinement Network for Saliency Detection"

BDRAR. Code for the ECCV 2018 paper "Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection"

MTMT. Code for the CVPR 2020 paper "A Multi-task Mean Teacher for Semi-supervised Shadow Detection"

pytorch-3dunet. 3D U-Net model for volumetric semantic segmentation written in pytorch

MICCAI2019. Python

liver_segmentation. Unet,Unet++,FPN,DAF implementations for liver segmentation