2 papers
cs.CV2025
Rethinking Visual Information Processing in Multimodal LLMs
Dongwan Kim, Viresh Ranjan, Takashi Nagata +2
Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mis…
cs.LG2024
Revisiting Machine Unlearning with Dimensional Alignment
Seonguk Seo, Dongwan Kim, Bohyung Han
Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. Wh…