Dr. Afshin Dehghan
Apple
Sr AIML Manager, Apple. Leading the Multimodal Intelligence Team in the Hardware Technology group.
Topic: Flexible Length Video Tokenization
Invited Talks
Invited speaker lineup announced.
Prof. Salman Khan
MBZUAI
Salman Khan is a researcher and educator at MBZUAI, known for work in deep learning, visual recognition, and multimodal learning for vision-language models.
Topic: Where Video Reasoning Fails - and What to Do About It
Prof. Hilde Kuehne
Univ. of Tübingen
Hilde Kuehne is a professor working on computer vision and multimodal machine learning, with widely recognized contributions in action recognition and video understanding.
Topic: Look, Listen, Adapt - Localization, Audio-Visual Reasoning, and Test-Time Adaptation for VideoLLMs
Prof. Lena Maier-Hein
German Cancer Research Center (DKFZ), Heidelberg University
Lena Maier-Hein is a professor and principal investigator at DKFZ and Heidelberg University, leading research in medical image computing, surgical data science, and AI for healthcare.
Topic: Don't Lose the Sponge: Advancing Long-Context Video Understanding for Surgical Safety
Dr. Gerard Medioni
Amazon
Gerard Medioni is a computer vision leader at Amazon and a long-time contributor to visual perception, 3D scene understanding, and video analytics research.
Topic: VideoLLMs in Prime Video
Prof. Mike Z Shou
NUS
Mike Z. Shou is a professor at the National University of Singapore whose research focuses on computer vision, multimedia analysis, and large-scale video understanding.
Topic: Unified Multimodal Video Understanding and Generation
Dr. Ruben Villegas
Google DeepMind
Ruben Villegas is a research scientist at Google DeepMind whose work centers on generative modeling for video, dynamics prediction, and learned world models.
Topic: Towards creating anything from any input: The Evolution of Multi-Modal Generative Models
Panel Discussion
Moderator: Prof. Rene Vidal
Panelists: TBD
Panel topic and details to be announced.