Kristen Grauman
University of Texas at Austin
Leads work on egocentric video understanding and retrieval at scale, with a focus on long-horizon grounding and efficient perception.Speakers
Mohit Bansal
University of North Carolina at Chapel Hill
Researches multimodal language/vision agents, grounded reasoning, and controllable generation for real-world tasks.
Dan Roth
University of Pennsylvania / Oracle AI
Pioneer in structured, grounded reasoning and robust inference for language/vision systems deployed in real settings.
Scott Wen-Tau Yih
Meta
Works on efficient retrieval and multi-hop QA, designing retrieval-augmented architectures that balance latency and quality.More to be announced
Leaders from Industry & Academia
Panel
From Retrieval to Action: What Should Agentic Vision Systems Verify?
Diverse perspectives across industry and academia.Workshop Organizers
Amit Agarwal
Oracle AI
Builds agentic vision systems and retrieval pipelines with grounded evidence and data enrichment at scale.
Vivek Gupta
Arizona State University
Researches heterogeneous retrieval over structured and unstructured sources, focusing on robust, grounded search.
Vivek Srikumar
University of Utah
Works on grounding, reliability, and structured prediction for language/vision systems.
Tao Sheng
Oracle AI
Focuses on agentic planning, tool use, and multimodal system integration for production deployments.
Alice Oh
KAIST
Leads work on multilingual attribution, grounding, and socially responsible AI across modalities.
Sara Hooker
Adaption Labs
Researches efficient and responsible ML (distillation, compression) to make large models deployable.
Jyotika Singh
Oracle AI
Works on agentic memory, data quality, and human-in-the-loop interaction for grounded systems.
Hitesh Patel
Oracle AI
Focuses on multilingual and multimodal responsible AI with grounded retrieval and safety.Program Committee
Karan Dua
Expertise in scaling multimodal data pipelines and synthetic generation for generative model training. Advances the field through the design of calibrated metrics and comprehensive benchmarking for generative AI.
Hansa Meghwani
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.
Meizhu Liu
Holds a PhD from the University of Florida. Specializes in the development of multimodal retrieval architectures and generative tools for image editing. Over 70+ publications in top-tier conferences.
Michael Avendi
Holds a PhD from UC Irvine. Focuses on generative AI, vision-language-action models, and robotics learning to bridge perception and physical autonomy.
Matthew Rowe
Researches multimodal and hybrid search with a focus on enterprise-scale RAG. Specializes in architecting retrieval systems for high-throughput production deployments.
Yassi Abbasi
Holds a PhD from USC. Specializes in multimodal AI with an emphasis on image-text representation learning, generative modeling, and the design of robust evaluation metrics.
Peerat Limkonchotiwat
Research Fellow at AI Singapore, NUS. Leads SEA-LION, SEA-HELM, and SEA-Guard; collaborates on LLM, multimodal, safety, and dataset research. Contributor to SEACrowd and SEA-VL; invited researcher at Chulalongkorn University and SIGSEA advisory board member.
Taki Hasan
PhD candidate at Hanyang University, South Korea. Research focuses on trustworthy AI, including efficient test-time adaptation of vision-language and multimodal models for handling distribution shifts.
Praneet Pabolu
Holds a Master’s from Cornell and leads foundation model development at Splunk, focusing on representation learning and generative reasoning for complex environments.Stay connected
General inquiries
Reach out to the organizers with questions about submissions, sponsorship, or program.