SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang, Xuesong Niu, Tengyu Liu, Qing Li, Siyuan Huang
Keynote Speakers
Tim Meinhardt is a research scientist at the NVIDIA Dynamic Vision and Learning (DVL) group. His work focuses on video and scene understanding, specifically, multi-object tracking and video segmentation. In 2009, his academic journey started with a B.Sc in physics at the Ludwig Maximilian University (LMU) of Munich. After spending a semester abroad at the Boğaziçi University in Istanbul and finishing his Bachelor in 2013, he worked in Berlin and Munich as a software engineer for web development and robotics. He returned to academia in 2014 for a M.Sc. in Computer Science at the LMU of Munich. For his master’s thesis, he joined the Computer Vision & Artificial Intelligence (CVAI) chair at the Technical University of Munich (TUM). Under the supervision of Prof. Dr. Laura Leal-Taixé and as a member of her TUM DVL group, he continued his research as a Ph.D. candidate until 2023.
Or Litany is a Senior Research Scientist at NVIDIA and an Assistant Professor at the Technion,
specializing in 3D computer vision and generative AI.
He is honored to be a 2023 Azrieli Faculty Fellow and a Taub Fellow.
Previously, he conducted postdoctoral research at Stanford University under
Prof. Leonidas Guibas, and at FAIR, hosted by Prof. Jitendra Malik.
His PhD is from Tel-Aviv University, advised by Prof. Alex Bronstein.
My B.Sc. in Physics and Mathematics is from the Hebrew University.
Alex Bewley, a Senior Researcher at Google DeepMind, works at the intersection of computer vision and robotics,
focusing on combining language, 3D scene understanding, and methods that leverage spatial or temporal structure for high-speed agile robotics.
He has explored the use of large datasets in an open vocabulary setting, notably through his work on Scene Graph ViT and Video OWL-ViT.
He also co-authored the award-winning Open X-Embodiment dataset, contributing to the advancement of large-scale robotic learning.
Alex obtained his PhD in robot vision from the Queensland University of Technology in Australia.
His goal is to enable multi-purpose robots that can handle everyday tasks and adapt to new ones described in natural language.
Krishna Murthy Jatavallabhula is a AI research scientist at Meta.
Previously, he was a postdoc at MIT CSAIL with Antonio Torralba and Josh Tenenbaum.
Prior to that, I received my PhD at Universite de Montreal and Mila, advised by Liam Paull.
His research focuses on building world models for robots and other physical agents to enable them
to perceive, reason, and act just as humans are able. My work spans the robotics, computer vision, and machine learning communities.
His work has been recognized with PhD fellowship awards from NVIDIA and Google, and a best-paper award from IEEE RAL.
