Saehyung Lee

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models

Enhancing Factuality in Detailed Image Captioning with LLM-MLLM Collaboration

Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors

DAFA: Distance-Aware Fair Adversarial Training

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection

ProtoReg: Prioritizing Discriminative Information for Fine-grained Transfer Learning

Prototypical Influence Function for Fully Test-time Adaptation

Reduce, Reuse, and Recycle: Navigating Test-Time Adaptation with OOD-Contaminated Streams

Revisiting the Lottery Ticket Hypothesis for Pre-trained Networks