Stars
Dual Attention Network for Scene Segmentation (CVPR2019)
Fast and Universal 3D reconstruction model for versatile tasks
[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Official PyTorch Implementation of "Latent Diffusion Model Without Variational Autoencoder".
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
Official implementation of "Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting" (https://arxiv.org/abs/2405.06419)
[CVPR 2025] Official implementation of "AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation Nowcasting"
About Code release for "MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions" (CVPR 2021) https://arxiv.org/abs/2103.02243
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / veRL/ Swift / Ultra…
Implementation of DeepMind's Deep Generative Model of Radar (DGMR) https://arxiv.org/abs/2104.00954
This is the implementation code of the paper(Skilful precipitation nowcasting using deep generative models of radar) Edit by Ziyu Wang
Skilful precipitation nowcasting using deep generative models of radar
Python framework for short-term ensemble prediction systems.
Official MegEngine implementation of RepLKNet
Wavelet Convolutions for Large Receptive Fields. ECCV 2024.
[AAAI 2026]"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection"
(IJCV2024 & ICCV2023) LSKNet: A Foundation Lightweight Backbone for Remote Sensing
Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising (AAAI 2025)
[Information Fusion 2025] Official implementation for "MMIF-INet: Multimodal medical image fusion by invertible network"
Official PyTorch Code for Paper: Video Prediction Transformers without Recurrence or Convolution
[TNNLS 2025] TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition
Fast and memory-efficient exact attention