3 papers
cs.AI2026
Seeing Depth but Choosing Cues in Vision-Language Models
Zhengtao Zou, Pekka Marttinen
Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through controlled depth--cue conflicts,…
cs.CV2026
Latent-Compressed Variational Autoencoder for Video Diffusion Models
Jiarui Guan, Wenshuai Zhao, Zhengtao Zou +2
Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction.…
cs.CV2025
Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
Zhengtao Zou, Ya Gao, Jiarui Guan +2
Large Vision-Language Models (LVLMs) typically process visual inputs as a prefix to the language decoder. As the model autoregressively generates text, this initial visual informat…