Code for the paper "Fusing Satellite Imagery and Planimetric Maps for Cross-View Localization"

VecLang source code

DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images

ARM: An AutoRegressive Large Multimodal Model with Discrete Representations

Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models

🔥 Official code repository for "Unlocking Dense Metric Depth Estimation in VLMs"

A high performance 3DGS renderer

[CVPR 2026 Oral] VGGT Omega

A feed-forward 3D foundation model for reconstructing scenes from streaming data

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

This is the repo for paper "OccSim: Multi-kilometer Simulation with Long-horizon Occupancy World Models"

(CVPR 2026) Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion

A simple video streaming baseline that outperforms SOTAs.

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

[CVPR 2026 Findings] Speed3R: Sparse Feed-forward 3D Reconstruction Models

[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

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

[CVPR2026] SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving

[ECCV 2024] This is the official implementation of HRMapNet, maintaining and utilizing a low-cost global rasterized map to enhance online vectorized map perception.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

[CVPR 26] Release repo of our work "Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers"

Reference PyTorch implementation and models for DINOv3

[ICLR2026] WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

[ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning

Tooling for the Common Objects In 3D dataset.

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)