3 papers
cs.CV2026
DVTR-KD: Distilling Vision-Language Models via Intermediate Visual Token Reconstruction
Haolan Wei, Jiahui Wang, Junli Zha +4
Multimodal large language models (MLLMs) have achieved strong performance on diverse vision-language tasks, but their computational demands limit deployment under constrained budge…
cs.CV2026
Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models
Junli Zha, Jiahui Wang, Xinkai Lu +1
Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a tra…
cs.CV2020
Video Object Segmentation with Episodic Graph Memory Networks
Xiankai Lu, Wenguan Wang, Martin Danelljan +3
How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segm…