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.

CLIP's Visual Embedding Projector is a Few-shot Cornucopia

DITA Open Toolkit — the open-source publishing engine for content authored in the Darwin Information Typing Architecture.

✈️ Accelerating Vision Diffusion Transformers with Skip Branches.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

official code of CVPR2025 Evolsplat

Official repository for CVPR 2025 paper: OpenSDI: Spotting Diffusion-Generated Images in the Open World

Code for LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation (CVPR2025)

Official repository for the paper "Surg-3M: A Dataset and Foundation Model for Perception in Surgical Settings".

[CVPR 2025] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

[CVPR 2025] PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding

[CVPR'25] Official PyTorch implementation of AvatarArtist: Open-Domain 4D Avatarization.

This repo holds the implementation of PAVE: Patching and Adapting Video Large Language Models (CVPR2025)

Code for "CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning"

Scaling Vision Pre-Training to 4K Resolution

[CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

The official code of Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective.

[CVPR 2025] Good Keypoints for the Two-View Geometry Estimation Problem. The reference implementation of the paper.

2D Gaussian Splatting based LiDAR Odometry And Mapping

Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"

Beyond Accuracy: What Matters in Designing Well-Behaved Models?

[CVPR'25] NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting