Invited Talks

박경문 교수
(고려대)

Biography
TBD

Towards Privacy-Preserving Generative Intelligence (45분)

TBD

이동하 교수
(연세대)

Biography
TBD

Towards Reasoning-Centric Personalized AI Systems and Agents (45분)

TBD

최윤석 교수
(Texas A&M University)

Biography
TBD

TBD (45분)

TBD

백성용 교수
(한양대)

Biography
TBD

TBD (45분)

TBD

전광성 교수
(POSTECH)

Biography
TBD

Frontiers of Offline Interactive Machine Learning: From Contextual Bandits to LLM Alignment (45분)

TBD

서지원 교수
(서울대)

Biography
TBD

TBD (45분)

TBD

김태현 교수
(한양대)

Biography
TBD

Generating Real-World Image Degradations (45분)

TBD

송길태 교수
(부산대)

Biography
2016-현재	부산대학교 정보컴퓨터공학부 교수
2026-현재	부산대학교 정보의생명공학대학장
2020-현재	부산대학교 인공지능융합연구센터장
2025-현재	과학기술정보통신부 AI대학원협의회 이사
2022-현재	한국정보과학회 부회장 (‘24~’25) / 이사 (’22, ‘26)
2022-현재	한국정보과학회 인공지능소사이어티 부회장
2019-현재	부산대학교병원 융합의학기술원 의료인공지능연구실장
2026-현재	한국생명정보학회 이사
2018-현재	ISMB 프로그램 운영위원
2025	RECOMB CG 2025 워크샵 PC chair
2023, 2025	IEEE BigComp PC co-chair

Bridging Structure and Interpretability: From Hypergraph Knowledge Inference to Adaptive Multi-Branch Decision Trees (45분)

As machine learning models are increasingly deployed in high-stakes domains, the dual demands for powerful representation learning and transparent interpretability have become paramount. This talk presents two distinct, novel architectures designed to tackle these challenges across both complex relational data and tabular prediction datasets.

First, we introduce the Hypergraph Interaction Transformer (HIT), a deep representation learning model engineered to infer knowledge across multiple known ontologies. By leveraging hypergraph structures of heterogeneous entities and employing attention-based learning, HIT successfully captures intricate, multi-entity relationships to discover novel knowledge and identify missing associations with state-of-the-art performance and explicit explainability.

Second, shifting the focus to interpretable tabular modeling, we address the under-expressiveness of conventional binary decision trees under strict maximum-depth constraints. We present the Multi-Branch Neural Decision Tree with Adaptive Pruning (MBNDT), a novel framework for shallow-depth tree induction. Trained end-to-end with differentiable multi-way splits, MBNDT learns ordered thresholds over selected features alongside an adaptive branch mask that dynamically optimizes its effective arity. The resulting model is then converted into a deterministic single-path tree for highly efficient, human-readable inference.

Together, these methodologies illustrate how leveraging advanced structural representations and dynamic routing mechanisms can drastically push the frontiers of Explainable AI (XAI) without sacrificing predictive power.