Authors

Yupeng Hu

Publications 2

Preprint Open access

GroundSight at GroundLM 2026 Shared Tasks: GoldenViewVQA

Kun Wang, Yupeng Hu, Ruping Cao et al. · 2026

GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making precise evidence localization as important as answer correctness. We present \textbf{CoVeR-VQA}, a training-free multi-stage verification and correction framework for gr …

Preprint Open access

VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models

Qianlong Xiang, Miao Zhang, Kun Wang et al. · 2026

Concept erasure is essential for the safe deployment of text-to-image diffusion models, as they may reproduce harmful, copyrighted, or privacy-sensitive content learned from unconstrained large-scale data. Existing methods typically erase unwanted concepts while preserving general generation capability by redirecting t …

Co-authors