Taehwan Kim

One More Glance with Sharp Eyes: Rethinking Lightweight Captioning as a Practical Visual Specialist

Diffusion Models as Intrinsic Distribution Estimators for Self-Verifying Inference-Time Scaling

ClueVQA: Enhancing Query Based Retrieval in Video-LLMs with Answer Clues

Multi-aspect Knowledge Distillation with Large Language Model

Designing Deep Learning Programs with Large Language Models