3 papers
cs.CV2026
Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
Junha Song, Byeongho Heo, Geonmo Gu +3
When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast…
cs.CV2026
RL makes MLLMs see better than SFT
Junha Song, Sangdoo Yun, Dongyoon Han +2
A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarka…
cs.CV2025
MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning
Junha Song, Yongsik Jo, So Yeon Min +4
Systems such as video chatbots and navigation robots often depend on streaming image captioning to interpret visual inputs. Existing approaches typically employ large multimodal la…