works on

From the 1 of 9 linked papers with an AI index.

collaborators

9 papers

cs.IR2026

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval

Suhyeong Park, Junha Jung, Jungwoo Park +1

The paper introduces SaMer, an object‑aware token merging method that compresses image tokens into a small set of centroids while keeping the late‑interaction interface for vision‑…

cs.AI2026

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

Yein Park, Jungwoo Park, Jaewoo Kang

Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstra…

cs.CL2025

The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models

Taewhoo Lee, Minju Song, Chanwoong Yoon +2

Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can repres…

cs.CL2025

LEME: Open Large Language Models for Ophthalmology with Advanced Reasoning and Clinical Validation

Hyunjae Kim, Xuguang Ai, Sahana Srinivasan +27

The rising prevalence of eye diseases poses a growing public health burden. Large language models (LLMs) offer a promising path to reduce documentation workload and support clinica…

cs.CL2025

Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards

Jaehoon Yun, Jiwoong Sohn, Jungwoo Park +9

Large language models have shown promise in clinical decision making, but current approaches struggle to localize and correct errors at specific steps of the reasoning process. Thi…

cs.LG2025

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models

Jungwoo Park, Taewhoo Lee, Chanwoong Yoon +2

Extreme activation outliers in Large Language Models (LLMs) critically degrade quantization performance, hindering efficient on-device deployment. While channel-wise operations and…