Jaewoo Kang

A novel LLM framework that adapts inference strategies based on question type leads to superior performance in biomedical question answering, clinching first place in a competitive evaluation.

Merging image tokens intelligently can cut storage costs by over 16 times while boosting retrieval accuracy, challenging the notion that less data always means less context.

Early-stage reasoning failures can be drastically reduced from 64% to 13% with a novel RL approach that penalizes cascading errors in medical VQA.

Fine-tuned small LLMs can significantly outperform commercial models in scam detection tasks, enabling faster and more effective responses to online scams.

Mechanistic analysis reveals how adversarial suffixes suppress the propagation of refusal-mediating directions in LLMs, and ASGuard offers a targeted intervention.