5 papers
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee +1
Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computat…
Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
Seonghoon Yu, Dongjun Nam, Dina Katabi +1
Knowledge Distillation (KD) aims to train a lightweight student model by transferring knowledge from a large, high-capacity teacher. Recent studies have shown that leveraging diver…
Latent Expression Generation for Referring Image Segmentation and Grounding
Seonghoon Yu, Junbeom Hong, Joonseok Lee +1
Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual descriptio…
A Simple Baseline with Single-encoder for Referring Image Segmentation
Seonghoon Yu, Ilchae Jung, Byeongju Han +4
Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, com…
Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation
Seonghoon Yu, Paul Hongsuck Seo, Jeany Son
We propose a new framework that automatically generates high-quality segmentation masks with their referring expressions as pseudo supervisions for referring image segmentation (RI…