Human-Centric AI:

Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy

Hyeju Shin* (ETRI & OpenNN, MODULABS), Vincent-Daniel Yun*^✝ (USC Viterbi & OpenNN, MODULABS), Kyudan Jung* (KAIST AI & OpenNN, MODULABS), Seongwon Yun* (Hanwha Life Insurance & OpenNN, MODULABS)

Incomplete Prompt Jailbreaks in Language Models

Yeonjea Kim* (KAIST AI), Bumjin Park* (KAIST AI), Jaesik Choi (KAIST AI, INEEJI)

Risk-adaptive Activation Steering for Safe Multimodal Large Language Models (🏅 Best Paper)

Jonghyun Park* (Seoul National University), Jonghyun Choi (Seoul National University)

FairPrune: A Bias-Aware Pruning Method for Stable Diffusion

Shubham Paliwal (TCS Research), Arushi Jain (TCS Research), Monika Sharma (TCS Research)

Exploring Gemini 2.5 for Explainable Deepfake Detection under Black-Box Constraints

Hyunjune Kim (Sungkyunkwan University), Hyeongjun Choi (Sungkyunkwan University), Simon S. Woo (Sungkyunkwan University)

HIVE: Human-In-the-Loop Framework for Explainable Recommender Systems with Veracity-Based Human Feedback

Yeonbin Son (University of Virginia), Bohyun Choi (Ewha Womans University), Jiyoun Park (Ewha Womans University), Yerim Choi (Ewha Womans University), Matthew L. Bolton* (University of Virginia)

Human as a Knowledge Augmenter in Human-AI Interaction

Yujin Cha (KAIST)

Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions

Jinyoung Choi (Seoul National University), Junoh Kang (Seoul National University), Bohyung Han (Seoul National University)

Fréchet Oral Distance: A Coordinate-Free Metric and Benchmark for Speech-Driven Oral Animation

Jaehong Myung* (Sogang University), Seungho Eum (Sogang University), Hyunjung Chung (Sogang University), Unsang Park^✝ (Sogang University)

Using Knowledge Graphs to Measure and Characterize the Interpretability of Deep Learning Interpretations

Mathieu d’Aquin (LORIA, Université de Lorraine, CNRS), Liudmyla Klochko (LORIA, Université de Lorraine, CNRS)

Can Large Language Models Detect and Explain Microaggressions? A Comparative Study with Human Evaluations

Ji Hye Kim (Sogang University), Cheol-Sung Lee (Sogang University), Eun-Kyoung Cho (Sogang University), Myoung-Wan Koo (Sogang University)

A Neo-Piagetian Framework for Understanding Anthropomorphic Response Patterns in Conversational Agents

San Hong (Seoul National University), Yejin Kang (Seoul National University), Woojin Park (Seoul National University)

BISeg: Band-Interval Selection for Explainable Hyperspectral Segmentation

Jaeik Bae (Gwangju Institute of Science and Technology), Yong-Gu Lee^✝ (Gwangju Institute of Science and Technology)

Adaptive Multimodal Fact-Checking with Visual Evidence Necessity

Jaeyoon Jung (Soongsil University, MAUM.AI), Yejun Yoon (Soongsil University), Kunwoo Park (Soongsil University)

Training-free VQA with Selective Meta-Reasoner for Interpretable Vision-Language Reasoning

Seungyeon Lee (Kyungpook National University), Wonjun Choi (Kyungpook National University), Dong-Gyu Lee* (Kyungpook National University)

ATTR: An Adaptable and Trustworthy Targeting Recommendation Framework under Real-World Constraints

Sanghyeon Lee* (LG Uplus Corp.), Jinmo Kang* (LG Uplus Corp.), Yeonghwan Jeon (LG Uplus Corp.), Hyuncheol Jo (LG Uplus Corp.), Byoung-Ki Jeon (LG Uplus Corp.)

Analyzing Spectral Information of Transformers

Vo Huu Anh Tuan (Korea University), Anh Tong (Korea University)

Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models

Seungho Cho (KAIST), Changgeon Ko (KAIST), Eui Jun Hwang (KAIST), Junmyeong Lee (KAIST), Huije Lee (KAIST), Jong C. Park* (KAIST)

Verbalized Uncertainty and Citation Match in LLM Question Answering: A Pilot Study on Adoption and Verification

Minjoon Sohn (Seoul National University), San Hong (Seoul National University), Woojin Park (Seoul National University)

Causal Inference-Based Sleep Stage Scoring under Cluster-level Unobserved Confounding

Yeongho Lee* (THYROSCOPE INC.), Kyubo Shin (THYROSCOPE INC.), W. Hong Yeo^✝ (Georgia Institute of Technology) Gi-Soo Kim^✝ (UNIST)

Development and Pilot Service of Multi-agents Specialized in Absolute and Relative Mandatory Items for Articles of Incorporation Review

Seokyoung Hong^✝ (Sogang University), Sua Kim (Sogang University), Naru Kang (Sogang University), Minhye Kim (DLG Law Corporation), Hyunji Jang (DLG Law Corporation), Myoung-wan Koo (Sogang University)

Fusing Heterogeneous Speech Tasks for Automated Dysarthria Severity Classification

Jaeyeong Lee (Sogang University), Hyung-Min Park (Sogang University)

Understanding the Impact of Quantization on Model Explainability

Seongwook Chung* (KAIST), Seongun Kim* (KAIST), Jaesik Choi^✝ (KAIST, INEEJI)

JoCE: Joint Counterfactual Explanation for Interpretable Time Series Anomaly Detection

Woojin Jeong (Seoul National University), Geonwoo Shin (Seoul National University), Jaewook Lee (Seoul National University)

Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation (🏅 Best Paper)

Flavio Giorgi (Sapienza University of Rome), Matteo Silvestri (Sapienza University of Rome), Cesare Campagnano (Pinecone), Fabrizio Silvestri (Sapienza University of Rome), Gabriele Tolomei (Sapienza University of Rome)

Attribution-Based XAI for Dysarthria Assessment: Validation of Acoustic Feature Attributions

Minseo Kim (Sogang University), Junseok Oh (Sogang University), Wonwoo Jeong (Sogang University), Ji-Hwan Kim (Sogang University)

TIMING: TEMPORALITY AWARE INTEGRATED GRADIENTS FOR TIME SERIES EXPLANATION (🏅 Best Paper)

Hyeongwon Jang* (KAIST), Changhun Kim* (AITRICS), Eunho Yang (KAIST, AITRICS)

Causal Diffusion Models for Controllable Counterfactuals

Junghyo Sohn (Korea University), Wootaek Jeong (Korea University), Sujeong Song (Korea University), Jee Seok Yoon (Korea University), Heung-Il Suk* (Korea University)