Xiaoyu Tang

AbyssSplat: Active-Illumination-Aware Gaussian Splatting for Deep-Sea 3D Reconstruction

A primary challenge in deep-sea 3D reconstruction is the strong coupling between active illumination and the participating water medium. Existing underwater 3D Gaussian Splatting (3DGS) methods typically model backscattering along pixel rays as a fixed constant, neglecting the distance-dependent attenuation of active l...

Visual transformer-based multi-relational perceptual network for facial expression recognition in the wild

CrACK: Adversarial Attacks on Cross-Model Consistency in Collaborative Vision Foundation Models

This work proposes CrACK (Cross-model Adversarial Consistency attack), an inference-time attack that exploits this interface without modifying any input pixel, model weight, or training data, and shows that it causes catastrophic degradation while every individual model continues to produce its unchanged standalone out...

SIPTraj: Map-Free End-to-End Trajectory Prediction via Physics-Guided Scene Interaction

Trajectory prediction of surrounding agents is a prerequisite for safe planning and decision making in autonomous driving. Without high-definition (HD) maps, sensor-derived bird's-eye-view (BEV) features provide no explicit lane topology or drivable-area priors, making it inherently difficult to ground each agent in it...

Test-Time Prototype Adaptation for Open-Vocabulary Semantic Segmentation

This work proposes Test-time Prototype Adaptation (TPA), a training-free plug-in that operates at the output level, leaving the host's forward pass and weights unmodified.