Blog

Research updates, lab news, and stories from VU Lab

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.

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.

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting

We propose Splat2BEV, a Gaussian Splatting-assisted BEV perception framework that aims to learn BEV feature representations that are both semantically rich and geometrically precise.

When 'YES' Meets 'BUT': Can AI Comprehend Contradictory Humor?
When 'YES' Meets 'BUT': Can AI Comprehend Contradictory Humor?

YESBUT studies whether AI systems can understand contradictory humor in comics by reasoning across paired visual situations and resolving the contrast between what appears true and what undermines it.

Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range
Expo-GS: Exposure-Aware Signed Distance Function in Gaussian Splatting for High Dynamic Range

Expo-GS introduces an exposure-aware signed distance formulation for Gaussian Splatting, targeting robust high dynamic range reconstruction under challenging illumination and exposure variation.

Latest Posts

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.

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.

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting

We propose Splat2BEV, a Gaussian Splatting-assisted BEV perception framework that aims to learn BEV feature representations that are both semantically rich and geometrically precise.