A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond

(ICML2026) Official implementation of VLANeXt.

A local AI assistant running on your device. It turns your files into actionable memory.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"

[CVPR 2022] Unsupervised Image-to-Image Translation with Generative Prior

[NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Code for ShadeGAN (NeurIPS2021)

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

Code repo for "FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation" (ICCV 2021)

Code for Talk-to-Edit (ICCV2021). Paper: Talk-to-Edit: Fine-Grained Facial Editing via Dialog.

"3D Human Texture Estimation from a Single Image with Transformers", ICCV 2021 Oral

Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)

Path-Restore: Learning Network Path Selection for Image Restoration (IEEE TPAMI, 2021)

Code for C2-Matching (CVPR2021). Paper: Robust Reference-based Super-Resolution via C2-Matching.

Benchmarks for semi-supervised domain generalization.

Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

[CVPR 2021] Unsupervised 3D Shape Completion through GAN Inversion

Code for DISCNet.

Code for paper 'Audio-Driven Emotional Video Portraits'.

MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

The code for CVPR21 paper "Deep Animation Video Interpolation in the Wild"

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis