Schedule Released
Program schedule is live; acceptance notifications have been sent.
Program
General questions and accessibility requests: surgellm@googlegroups.com.

Organizing Committee

Photo of Vivek Gupta
Arizona State University
Assistant Professor, School of Computing and Augmented Intelligence
Researches trustworthy AI systems for complex multimodal and semi-structured data, including tables, charts, maps, and flowcharts.
Photo of Kaize Ding
Northwestern University
Assistant Professor of Statistics and Data Science
Leads research on data mining, machine learning, large foundation models, and reliable AI for autonomous decision-making.
Photo of Harsha Kokel
IBM Research
Research Scientist, AutoAI
Works on efficient knowledge-guided learning in structured and relational domains, with interests in planning and reinforcement learning.
Photo of Yue Zhao
University of Southern California
Assistant Professor, Thomas Lord Department of Computer Science
Builds reliable, robust, and scalable AI systems, including open-source anomaly detection and agent safety tools.
Photo of Amit Agarwal
Oracle AI
Principal Scientist
Builds agentic vision systems, retrieval pipelines, and grounded data-enrichment workflows at scale.
Photo of Yu Wang
University of Oregon
Assistant Professor, Department of Computer and Information Science
Works on data-quality-aware graph machine learning, trustworthy graph learning, and data-centric AI.
Photo of Michael Glass
Michael Glass
IBM Research
Research Scientist
Researches LLM-based solutions for natural-language understanding, table search, and retrieval-augmented systems.
Photo of Yu Zhang
Texas A&M University
Assistant Professor, Computer Science & Engineering
Leads the SKY Lab, with research in data mining, natural language processing, and AI for scientific discovery.
Photo of Kavitha Srinivas
Kavitha Srinivas
IBM Research
Research Staff Member
Works on semantic technologies, knowledge graphs, reasoning, planning, and enterprise-scale data systems.
Photo of Xiusi Chen
UCLA / UIUC
Postdoctoral Research Fellow, University of Illinois Urbana-Champaign
Researches reasoning, alignment, and decision-making for large language models and automated language agents.
Photo of Oktie Hassanzadeh
IBM Research
Senior Research Scientist, IBM T.J. Watson Research Center
Researches data curation, information integration, knowledge management, and extraction from heterogeneous structured and unstructured sources.
Photo of Qi Zhu
AWS
Applied Scientist, AWS Bedrock Core Science
Works on LLM optimization, structured knowledge, graph RAG, and graph machine learning for retrieval-augmented and agentic systems.
Photo of Shuaichen Chang
AWS AI Lab
AI Researcher, AWS AI Lab
Founding member of the AWS Bedrock RAG and Agentic AI Science team, working on robust AI systems for data, retrieval, and agents.
Photo of Yuan Luo
Northwestern University
Professor and Chief AI Scientist, NUCATS
Researches machine learning, natural language processing, time series analysis, integrative genomics, and big-data analytics for medical and clinical applications.

Program Committee

Photo of Hitesh Patel
Oracle AI
Multimodal Responsible AI & IR
Focuses on multilingual and multimodal responsible AI with grounded retrieval and safety.
Photo of Eun Woo Im
Arizona State University
Multimodal Reasoning, Retrieval & Video Understanding
Ph.D. student at ASU focused on multimodal reasoning, retrieval, and its application to video understanding.
Photo of Tampu Ravi Kumar
Tampu Ravi Kumar
Arizona State University
Multimodal Reasoning, QA & Audio Reasoning
Ph.D. student at ASU focused on multimodal reasoning, QA over structured and unstructured data, and speech disfluency and audio reasoning.
Photo of Manan Roy Choudhury
Manan Roy Choudhury
Arizona State University
LLM Reasoning, Planning & Robustness
Ph.D. student at ASU focused on LLM reasoning and planning, anomaly and discrepancy detection, multi-modal robustness and perturbation analysis, and adversarial attacks in agentic frameworks.
Photo of Tejas Anvekar
Arizona State University
Personalized & Trustworthy MLLM Evaluation
Ph.D. student at ASU specializing in the personalized and trustworthy evaluation of MLLMs. Develops agent-driven, explainable frameworks to identify risks and bias across diverse tasks.
Photo of Hansa Meghwani
Hansa Meghwani
Enterprise RAG, Agentic Workflows & LLM/VLM Evaluation
Holds an MSc from LJMU, UK. Specializes in the architecture of enterprise-grade RAG and agentic workflows with a focus on attribution. Expertise spans the rigorous evaluation of multilingual LLMs and VLMs.
Photo of Jyotika Singh
Jyotika Singh
Oracle AI
Agentic Memory, Data Quality & Human-in-the-loop Interaction
Works on agentic memory, data quality, and human-in-the-loop interaction for grounded systems.
Photo of Bhargava Kumar
Bhargava Kumar
TD Securities
AI Strategy, Agentic Workflows & Financial Markets
Director at TD Securities, where he leads the AI Practice and supports AI strategy to production delivery for financial markets. He is currently focused on building agentic solutions to support business workflows across the firm. He has co-authored papers at ICLR, ICML, and ACL, among others, and reviews for major ML and NLP conferences. He holds an MS in Operations Research from Columbia University.
Photo of Tejaswini Kumar
Tejaswini Kumar
Apple
Applied AI, Generative AI & Agentic Systems
Senior Engineering Program Manager at Apple with a strong interest in applied AI, particularly generative AI and agentic systems. Her published research appears at ACL, NAACL, and AACL, among other venues. She holds an MS from the Industrial Engineering and Operations Research (IEOR) department at Columbia University.
Photo of Abhijit Chakraborty
MongoDB / Arizona State University
Knowledge Graph Embeddings, Federated RAG & Trustworthy Multi-agent AI
Technical Sales Director for North America Solution Consulting at MongoDB and a Computer Science Ph.D. candidate at Arizona State University's CoRAL Lab, with nearly two decades of experience building data platforms and AI systems across Fortune 500 enterprises. His research spans knowledge graph embeddings, federated retrieval-augmented generation, and trustworthy multi-agent AI, with recent work submitted to venues like NeurIPS and EMNLP. He serves the community as a NeurIPS and EMNLP 2025 reviewer, a Harvard Business Review Board of Advisors member, and an open-source contributor for Apache.
Photo of Yash Shah
Yash Shah
JPGlobal / Arizona State University
Diffusion Language Models, Federated RAG & Reliable Agentic AI
Applied AI Intern at JPGlobal and an M.S. Computer Science thesis candidate at Arizona State University, working on scalable AI systems. His research spans diffusion language models, federated RAG, and reliable agentic AI systems, with work accepted at ACL and EACL.
Photo of Ashish Raj Shekhar
Ashish Raj Shekhar
Arizona State University
AI in Education, AI Safety & Multi-agent Systems
M.S. Computer Science student at Arizona State University's CoRAL Lab, advised by Dr. Vivek Gupta. His research spans AI in education, AI safety, and multi-agent systems, with work accepted at EACL and ACL. He previously worked as a Data Engineer at Amazon and LendingKart.