3 papers
cs.CV2026
IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting
Fanye Kong, Hongyu Xia, Yu Zheng +3
Recent advances in deep learning have notably improved steganographic message hiding. However, designing a generalizable steganographic approach for 3D Gaussian Splatting (3DGS) th…
cs.CV2026
Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation
Boyang Gong, Yu Zheng, Fanye Kong +2
Like a body at rest that stays at rest, we find that visual attention in multimodal large language models (MLLMs) exhibits pronounced inertia, remaining largely static once settled…
cs.CV2025
Learning Counterfactually Decoupled Attention for Open-World Model Attribution
Yu Zheng, Boyang Gong, Fanye Kong +6
In this paper, we propose a Counterfactually Decoupled Attention Learning (CDAL) method for open-world model attribution. Existing methods rely on handcrafted design of region part…