7 papers
SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis
Juho Jung, Seongjae Kang, Mijoo Kim +4
Pixel-level annotation for chest X-ray (CXR) lesion segmentation is expensive, making active learning (AL) essential. However, existing AL strategies fail to account for the spatia…
PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
Seongjae Kang, Taehyung Yu, Sung Ju Hwang
Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligibl…
Best-of- TTS Evaluation is Confounded by ASR Family Alignment
Taehyung Yu, Seongjae Kang
Best-of- (BoN) inference improves content consistency in zero-shot text-to-speech by selecting among multiple candidates with an automatic speech recognition (ASR) verifier. We…
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
Seongjae Kang, Taehyung Yu, Sung Ju Hwang
LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a s…
Automated Structured Radiology Report Generation with Rich Clinical Context
Seongjae Kang, Dong Bok Lee, Juho Jung +3
Automated structured radiology report generation (SRRG) from chest X-ray images offers significant potential to reduce workload of radiologists by generating reports in structured…
PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models
Seongjae Kang, Dong Bok Lee, Hyungjoon Jang +2
Knowledge distillation (KD) is a widely used framework for training compact, task-specific models by transferring the knowledge from teacher models. However, its application to act…
Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
Seongjae Kang, Dong Bok Lee, Hyungjoon Jang +1
Semi-supervised learning (SSL) has emerged as a practical solution for addressing data scarcity challenges by leveraging unlabeled data. Recently, vision-language models (VLMs), pr…