works on

From the 1 of 14 linked papers with an AI index.

collaborators

14 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.CL2026

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b

Taeyun Roh, Eunha Lee, Wonjune Jang +3

Biomedical question answering requires not only accurate extraction of information from scientific literature but also reliable integration of evidence across multiple documents. T…

cs.CV2026

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Junha Jung, Minbyul Jeong, Suhyeon Lim +5

Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on…

cs.CL2026

Teaching Language Models to Think in Code

Hyeon Hwang, Jiwoo Lee, Jaewoo Kang

Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL) reasoning with code executio…

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.AI2026

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training

Yein Park, Minbyul Jeong, Jaewoo Kang

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (…