Industry Session Program

Session 1: RAG, LLM and Knowledge Graphs

Paper	Type
N206 — RAG-CUE: Actionable and Unified Evaluation for Retrieval-Augmented Generation Systems Prabhat Kumar Prabhakar, Neelesh Kumar Shukla, and Viji Krishnamurthy	Regular
N257 — Mix-of-Overlap: Enhancing Retrieval-Augmented Generation with Multi-Overlap Chunking Mahdi Ben Ameur, Mohamed Ali Fathallah, and Takoua Abdellatif	Short
N263 — Improving LLM Retrieval with GraphRAG-SF: Semantic Filtering for Graph-Based RAG Systems Mohammad-Parsa Hosseini, Ankit Shah, Connie Miao, and Wei Wei	Short
N283 — EICopilot: Search and Explore Enterprise Information over Large-scale Knowledge Graphs with LLM-driven Agents Yuhui Yun, Huilong Ye, Jingfeng Deng, Ruojia Li, Xinru Li, Li Li, and Haoyi Xiong	Short
N260 — LLM on a Budget: Active Knowledge Distillation for Efficient Classification of Large Text Corpora Viviana Luccioli, Rithika Iyengar, Ryan Panley, Flora Haberkorn, Xiaoyu Ge, Leland Crane, Nitish Sinha, and Seung Jung Lee	Regular
N274 — Beyond Characters: Position-Aware Metric and a Lightweight LLM for Low-Resource Bangla Punctuation Restoration Md Mehedi Hasan, S M Jishanul Islam, AKM Shahariar Azad Rabby, and Fuad Rahman	Short

Session2: Fraud, Finance & Risk Analytics

Paper	Type
N245 — FraudCenGCL: Role-Aware Graph Contrastive Learning for Low-Homophily Fraud Detection Seonkyu Lim, Jeongwhan Choi, and Jaehoon Lee	Regular
N254 — CleverCatch: A Knowledge-Guided Weak Supervision Model for Fraud Detection Amirhossein Mozafari, Kourosh Hashemi, Erfan Shafagh, Soroush Motamedi, Azar Taheri Tayebi, and Mohammad Tayebi	Regular
N237 — High Performance Fraud Detection at Scale Nitish Garg, Neeraj Vashistha, Varun Chugh, Nana Yaw Essuman, and Subigya Upadhyay	Short
N235 — Cash-flow Prediction Model Using Graph Neural Networks and Spatiotemporal Information from Double-entry Bookkeeping Data Ryoki Motai, Masato Kamebuchi, Sora Watanabe, Ryo Matsumoto, Keiichi Azuma, and Yukihiko Okada	Regular

Session3: Large Scale Data Systems

Paper	Type
N212 — Auto-reconfigurable Storage Structure to Minimize Read Access Time of Time-Series Data in Digital Twins Takafumi Onishi and Yasuhiko Kanemasa	Regular
N226 — Joining the Dots: Efficient Joins over Parent-Child Ordered Postings Lists Karthikeyan Ramasamy, Yupeng Fu, Jinny Wang, Philip Chan, Tejas Naik, George Zhai, and Shubham Gupta	Regular
N204 — A Robust and Efficient Pipeline for Enterprise-Level Large-Scale Entity Resolution Sandeepa Kannangara, Arman Abrahamyan, Daniel Elias, Thomas Kilby, Nadav Dar, Luiz Pizzato, Anna Leontjeva, and Dan Jermyn	Regular
N230 — Optimizing Product Deduplication in E-Commerce with Multimodal Embedding Aysenur Kulunk, Berk Taskin, M. Furkan Eseoglu, and H. Bahadir Sahin	Short
N207 — Question-to-Knowledge (Q2K): Multi-Agent Generation of Inspectable Facts for Product Mapping Wonduk Seo, Taesub Shin, Hyunjin An, Dokyun Kim, and Seunghyun Lee	Short

Session4: Enterprise AI & Applied Automation

Paper	Type
N261 — Automated Single-Turn Solution Recommendation System for Software IT Support Tickets Paulina Toro Isaza, Michael Nidd, Noah Zheutlin, Jae-wook Ahn, Chidansh Amitkumar Bhatt, Ruchi Mahindru, Martin Franz, Hans Florian, and Salim Roukos	Regular
N202 — Ontology-Driven Multimodal Framework for Automated Interpretation and Description of Architecture Diagrams Sakthivel Thangaraj, Neelesh Kumar Shukla, and Viji Krishnamurthy	Regular
N215 — FeatureCuts: Feature Selection for Large Data by Optimizing the Cutoff Andy Hu, Devika Prasad, Luiz Pizzato, Nicholas Foord, Arman Abrahamyan, Anna Leontjeva, Cooper Doyle, and Dan Jermyn	Regular
N231 — A Two-Stage Framework for Explainable Clustering in Public-Sector Analytics: Algorithm Selection and Post-Hoc Validation Jorge Queiroz	Short

Session5: Mobility, law, & Society

Paper	Type
N248 — Exploiting the Randomness of Large Language Models (LLM) in Text Classification Tasks: Locating Privileged Documents in Legal Matters Keith Huffman, Jianping Zhang, Nathaniel Huber-Fliflet, and Fusheng Wei	Regular
N250 — Adoption-weighted Technology Function Matrix for Big Data Patent Analytics in Smart Elderly Care Usharani Hareesh Govindarajan, Qian Gui, Gagan Narang, and Alessandro Galdelli	Short
N228 — Classification of Strategic Patents under the Scarcity of Labeled Data Kohdai Toyoda, Yoshimasa Utsumi, Ken Kobayashi, and Kazuhide Nakata	Short
N251 — Disinformation Analysis on Telegram: A Metadata-Centered, Privacy-Aware Dataset Jeong-Eun Choi, Karla Schäfer, York Yannikos, and Martin Steinebach	Regular
N217 — The Convergence of Sports, Technology, and Personalization Jacob Fagin, Rivver Gonzalez, Hanish Moola, and Varun Chugh	Short
N239 — Privacy-Preserving Synthetic Dataset of Individual Daily Trajectories for City-Scale Mobility Analytics Jun'ichi Ozaki, Ryosuke Susuta, Takuhiro Moriyama, and Yohei Shida	Short

Session6: ML for Industrial applications

Paper	Type
N225 — S2TKD: Dual-Student Knowledge Distillation for Industrial Visual Anomaly Detection and Localization Changyi Li, Chao Yang, and Yu Xiao	Regular
N208 - An Integrated Deep Learning Framework for Trading Card Grading: Design, Deployment, and Evaluation Lutfun Nahar, Md. Saiful Islam, Mohammad Awrangjeb, and Rob Verhoeve	Short
N216 - SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection Peizhe Zhao and Shunbo Jia	Short
N247 - Accelerating Industrial Geological Stratification from Well Logs with Deep Learning and Statistical Constraints Yuchen WANG, Ghali LARAQUI HOUSSAINI, Yuchen Hou, Shwetha Salimath, Sylvain Wlodarczyk, and Francesca Bugiotti	Short
N242 - When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping Youngjoon Lee, Hyukjoon Lee, Jinu Gong, Yang Cao, and Joonhyuk Kang	Short

Organizer