Posts

Imagine watching a concert not from a fixed camera angle, but from any angle. The catch? Volumetric video is incredibly hard to store and stream, and you can have the most photorealistic 4D scene in the world, but if you can't get it to a viewer efficiently, it's stuck in a lab. Our work, PackUV, tackles exactly this problem.

In this paper, we leverage a 3D Geometric Foundation Model to build a self-supervised pipeline that evaluates 3D consistency in AI-generated videos. By integrating our video generation model with reinforcement learning, we are able to generate highly 3D-coherent and realistic videos. This approach significantly reduces morphing, flickering, and artifacts, outperforming current state-of-the-art methods.

No stranger to controversy, AI pioneer Yann LeCun told a capacity crowd that large language models are not the future of AI and that a new approach is needed if machines are to achieve human-like intelligence.

As a tool for researchers, lawmakers, journalists and the public, the CNTR AISLE Portal provides analysis of state- and federal-level AI bills pending across the U.S.

Brown CS alum and Advisory Board member danah boyd has just received a Sloan Research Fellowship, recognizing her as one of the most promising scientific researchers working today, part of the next generation of U.S. and Canadian scientific leaders.

Less than a year after a receiving one of the highest honors in the field of virtual reality, Brown CS alum and former adjunct research faculty member and visiting scholar Joseph J. Laviola Jr. (now Charles N. Millican Professor of Computer Science at the University of Central Florida) has been recognized again.

The event featured participation from more than 400 university students from across the country and 1,000 students from 76 different countries participating virtually. Brown CS concentrators on three separate teams came home with awards.
 

The Sunlab is no longer with us. Students who graduated in the past decade or so think of it mainly as a place where they could use desktop computers running Linux and attend TA hours and help sessions. But it started as something different.

Brown CS is mourning the loss of Professor Emeritus of Computer Science Stanley (Stan) B. Zdonik, Jr., who passed away on February 5 at the age of 78. Stan was a distinguished computer scientist who made pioneering contributions to data management, with especially notable work in object-oriented databases, column-store architectures, and stream processing.

Almost thirty years after earning his doctorate from Brown CS, Yi-Jing Lin’s phone rang, and his already unconventional career took an unexpected turn.