High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

ICLR 2024 (Spotlight)

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Official implementation of Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model (ICLR 2025 Oral)

The official implementation of AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP

U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking

Official implementation of "Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals" (NeurIPS 2025)

A Pytorch implement of medical image segmentation U-shape architecture benchmarks

[ISBI 2024 Oral] Official Pytorch Code base for "CMUNeXt: An Efficient Medical Image Segmentation Network based on Large Kernel and Skip Fusion"

[ISBI 2023] Official Pytorch implementation of "CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network"

The official implementation of "ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training"

[MICCAI 2025] Official code for "Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster"

[MedIA 2025] MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation

[ICLR 2025] Official code of Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement

[MedIA 2025] Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation

[MICCAI 2024] HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training

The official repo for ”[WACV2025] Towards Accurate Unified Anomaly Segmentation“