Research

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.

Embodied AI 3D Vision VLM Reasoning

3DGS Spatial Memory Zero-Shot Exploration Embodied 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.

Embodied AI 3D Vision

Autonomous Driving 3DGS BEV Perception

[TPAMI'26 & NeurIPS'24 (Oral)] 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.

VLM Reasoning Benchmarking

Humor Understanding Comparative Reasoning Multimodal AI

[ICML'26] 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.

3D Vision

3DGS High Dynamic Range Scene Reconstruction

[NeurIPS'25] Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

We propose Segment then Splat, an Open-vocabulary 3D segmentation method that reverses the long established approach of “segmentation after reconstruction” by dividing Gaussians into distinct object sets before reconstruction.

3D Vision

3D Scene Understanding 3DGS Open-Vocabulary Segmentation

[NeurIPS'25] Praxis-vlm: Vision-grounded decision making via text-driven reinforcement learning

Praxis-VLM studies vision-grounded decision making through text-driven reinforcement learning, connecting visual observations with language-guided policy learning.

VLM Reasoning Embodied AI Human-Centered AI

Decision Making Reinforcement Learning

[NeurIPS'25] Fix False Transparency by Noise Guided Splatting

We propose Noise Guided Splatting, a method that handles the inherit “false transparency” artifact in 3DGS by injecting opaque noise Gaussians in the object volume during training, the object surfaces are encourages surface Gaussians to adopt higher opacity.

3D Vision

3D Reconstruction 3DGS

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.

VLM Reasoning Survey

Spatial Intelligence

[EMNLP'24 &25] Viva: Human-Centered Situational Decision-Making

VIVA & VIVA+ advances human-centered situational decision-making for multimodal AI, evaluating how models reason about visual context, human values, and action choices.

VLM Reasoning Human-Centered AI

Situational Decision Making Vision-Language Models Benchmarking

Balancing Fidelity and Diversity: Synthetic Data Could Stand on the Shoulder of the Real in Visual Recognition

Investigates how data fidelity and diversity affect recognition performance through synthetic data curation, offering training-free improvements for visual recognition tasks.

Generative Models

Synthetic Data Data Curation

[CVPR'25] 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.

3D Vision

3DGS Dynamic Scene Reconstruction Blur Robustness

CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data

A 19-dataset benchmark evaluating causal reasoning capabilities in vision models, revealing that performance drops sharply as causal complexity increases.

VLM Reasoning 3D Vision Benchmarking

Visual Causality

NEBULA: A Unified Framework for Evaluating Embodied AI Systems

A unified ecosystem for evaluating embodied AI systems beyond coarse task success metrics, combining capability tests for fine-grained skill diagnosis and stress tests for robustness under real-world perturbations.

Embodied AI Benchmarking

RT-LTP: Real-Time Latent Trajectory Prediction via Efficient Online Adaptation

A real-time trajectory prediction framework that reformulates forecasting as a latent-space alignment problem. Achieves up to 54% faster adaptation and 9.9% higher accuracy across multiple autonomous driving benchmarks.

Embodied AI

Autonomous Driving Trajectory Prediction Online Adaptation

[ACM MM'24] View-consistent Object Removal in Radiance Fields

We introduce a novel RF editing pipeline that significantly enhances consistency by requiring the inpainting of only a single reference image. This image is then propagated across multiple views using a depth-based approach, to maintain consistencies.

3D Vision Generative Models

3D Editing NeRF Object Removal Multi-view Consistency