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

[CVPR25] Official implementation of `MobileMamba: Lightweight Multi-Receptive Visual Mamba Network.'

The official implementation of [CVPR 2025] "5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks".

[CVPR'25 (Highlight)] Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

Collection of awesome parameter-efficient fine-tuning resources.

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image …

This is the official repository of the paper: CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradations

[TIV-2025] Implementation for paper "Degradation Modeling for Restoration-enhanced Object Detection in Adverse Weather Scenes".

[ECCV 2024] The official code for "Dolphins: Multimodal Language Model for Driving“

SHIFT Dataset DevKit - CVPR2022

[COLM 2025] LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

YOLOE: Real-Time Seeing Anything [ICCV 2025]

The official implementation of "An Efficient and Mixed Heterogeneous Model for Image Restoration"

✨✨Latest Papers on Vision Mamba and Related Areas

[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

Official repo for Adaptive Rectangular Convolution

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

This is official implementtaion of "VmambaIR: Visual State Space Model for Image Restoration"

Pytorch implementation of CVPR 2025 paper, "MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration". The Code will be released very soon (Within 2 week)

Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Full Score, Highlight).

[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

[ACCV 2024] Source code of WalMaFa

Wan: Open and Advanced Large-Scale Video Generative Models

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos