Alibaba AMAP CV Lab ORG

No description.

No description.

No description.

No description.

【ICLR 2026】 Official implementation of [OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation]

No description.

Generative 3D Earth Model by AMap-cvlab

Official implementation of [AstraNav-World: World Model for Foresight Control and Consistency]

[Official] AstraNav-Memory: Contexts Compression for Long Memory. An image-centric memory framework for lifelong embodied navigation via visual context compression and Qwen2.5-VL. SOTA on GOAT-Bench & HM3D-OVON.

official implementation of [CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation]

No description.

High-precision document OCR with structured Markdown output

An AI model from a computer vision lab that converts scanned document images into structured Markdown, preserving tables as HTML and math formulas in LaTeX notation, running via a GPU inference script with weights downloaded from Hugging Face.

No description.

Real-Time Interactive World Simulation on a Single Desktop GPU.

【AAAI 2026 Oral】UniMapGen is a generative unified framework that autoregressively generates smooth and topologically consistent vectorized maps from multi-modal inputs, enabling scalable, occlusion-robust city-scale mapping without costly on-site data collection.

No description.

ACL 2026

No description.

No description.