Depth Anything 3

🔥 OneThinker: All-in-one Reasoning Model for Image and Video

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Learning Plug-and-play Memory for Guiding Video Diffusion Models

Official code for VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

A tool for matching points annotation

Universal Image Restoration Pre-training via Masked Degradation Classification

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) and "UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers"

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

DUSt3R: Geometric 3D Vision Made Easy

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

Cameras as Relative Positional Encoding

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

A list of papers about concept bottleneck models (CBMs)

[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

CVPR 2024-Improved Implicit Neural Representation with Fourier Reparameterized Training

[CVPR 2025] Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation

(NIPS 2025) OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis

[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"

[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent