Holistic Evaluation of Multimodal LLMs on Spatial Intelligence

Scaling Spatial Intelligence with Multimodal Foundation Models

Audio-driven Digital Human Generation Model

[ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

Office codebase for ICML 2025 paper "Core Knowledge Deficits in Multi-Modal Language Models"

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

Wan: Open and Advanced Large-Scale Video Generative Models

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Official implement of VGGT-Long

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

OmniGen2: Exploration to Advanced Multimodal Generation.

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

Open-source unified multimodal model

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

An AI Hedge Fund Team

This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reas…

[NeurIPS 2025] MLLMs Need 3D-Aware Representation Supervision for Scene Understanding

CUDA Python: Performance meets Productivity

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

[ICLR 2025] Track-On: Transformer-based Online Point Tracking with Memory, and [arXiv 2025] Track-On2: Enhancing Online Point Tracking with Memory

Official implementation of Continuous 3D Perception Model with Persistent State

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]

TAPIP3D: Tracking Any Point in Persistent 3D Geometry

Lets make video diffusion practical!

Universal Monocular Metric Depth Estimation

Code for the paper MultiPhys: Multi-Person Physics-aware 3D Motion Estimation (CVPR 2024)