About Us

VU Lab studies visual understanding and spatial intelligence for robust embodied systems. We focus on perception, spatial reasoning, and decision-making methods that help intelligent agents interpret complex environments and act reliably in the real world.

Our work spans scene understanding, 3D perception, language-guided reasoning, and spatial intelligence. This homepage now provides direct entry points to the lab team and research overview.

Highlights

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning

We utilize 3DGS serves as a persistent spatial memory for embodied navigation, enabling the agent to ''hallucinate'' optimal views for high-fidelity Vision-Language Model (VLM) reasoning.

Spatial Intelligence in Vision-Language Models: A Comprehensive Survey

A comprehensive survey addressing how VLMs currently lack spatial intelligence, covering recent advances, taxonomies, and evaluations toward building spatially intelligent AI.

BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting

BARD-GS is a novel approach for robust dynamic scene reconstruction that effectively handles blurry inputs and imprecise camera poses.

Visual Understanding Benchmark for Open-World Scenes

Our lab offers a diverse range of benchmarks, including YesBut, Nebular, Viva, and Causal 3D, focused on advancing open-world visual understanding and robotic interaction.

Focus Areas

• Visual understanding for complex real-world scenes
• Spatial intelligence for embodied reasoning and planning
• Scalable learning systems for perception and autonomy

Explore

Use the navigation above to browse the lab’s team, research, publications, and contact pages.