Organizing Committee

Santosh T.Y.S.S.

Santosh T.Y.S.S.

Amazon, USA

Applied Scientist on the Amazon AGI Foundations team, with research experience in legal NLP, document-centric NLP, and community-building across ACL and EMNLP workshops.

Amit Agarwal

Amit Agarwal

Oracle, USA

Principal Applied Scientist in Oracle AI working on unstructured, structured, and multilingual retrieval, evaluation, and source-linked generation across CV, IR, NLP, and multimodal systems.

Vivek Gupta

Vivek Gupta

Arizona State University, USA

Assistant Professor developing NLP methods for complex and semi-structured data such as tables, forms, flowcharts, and maps, with emphasis on structure-aware reasoning and evaluation.

Yova Kementchedjhieva

Yova Kementchedjhieva

MBZUAI, UAE

Assistant Professor in NLP at MBZUAI, working on interpretability, fine-grained vision-language representation and generation, and cultural adaptation of multimodal systems.

Aparna Garimella

Aparna Garimella

Adobe Inc, India

Research Scientist at Adobe Research working on natural language processing, computational social science, bias detection and mitigation, document intelligence, and information extraction.

Yufang Hou

Yufang Hou

IT:U Austria / IBM Research Europe

Professor of Natural Language Processing at IT:U Austria and Research Scientist at IBM Research Europe, with work spanning LLMs, fact-checking, knowledge representation, and human-centered NLP.

Workshop Challenge Organizers

Jyotika Singh

Jyotika Singh

Oracle AI

Works on agentic memory, tool use, and reliable reasoning for LLM and agent systems, with additional research on structured information and exact algorithmic tasks.

Karan Dua

Karan Dua

Oracle AI

Large-scale multimodal data pipelines, synthetic generation workflows, and evaluation benchmarks.

Hitesh Patel

Hitesh Patel

Oracle AI

Leads applied research on multilingual and multimodal enterprise AI, including evaluation, agentic routing, and guardrails for languages and domains underserved by frontier models.

Rahul Suresh

Rahul Suresh

Abaka AI

Provides technical and organizational leadership across Abaka AI and the DrDocBench challenge, spanning benchmark design, model evaluation, and data quality.

Xiaolong Luo

Xiaolong Luo

Harvard University

Develops multimodal and multi-task AI for healthcare, while evaluating the fidelity, calibration, and robustness of language-model reasoning over complex clinical data.

Alexandra Bezea-Tudor

Alexandra Bezea-Tudor

Abaka AI

Works on Abaka AI's research and challenge initiatives in multimodal AI, with a focus on data curation, model evaluation, human-in-the-loop workflows, and challenge operations.

Program Committee

Tampu Ravi Kumar

Tampu Ravi Kumar

Multimodal reasoning, QA over structured and unstructured data, and speech/audio reasoning.

Hansa Meghwani

Hansa Meghwani

Enterprise RAG, agentic workflows, attribution, and multilingual LLM/VLM evaluation.

Contact

For questions about the workshop, reach out at: