Events

A foremost longstanding open problem in the Ribe program is to find a purely metric reformulation of the Banach space property of having an equivalent norm whose modulus of uniform smoothness has a given power type. In this talk we will present a solution of this problem. All of the relevant background and concepts will be explained, and no prerequisites will be assumed beyond rudimentary undergraduate functional analysis and probability. Based on joint work with Alexandros Eskenazis.  

Recent years have brought remarkable progress in 3D vision problems like view synthesis and inverse rendering. Despite these advancements, substantial challenges remain in material and lighting decomposition, geometry estimation, and view synthesis—particularly when handling a wide range of materials. In this talk, I will outline a few of these problems and present solutions that combine the principled structure and efficiency of physics-based rendering with the strong priors encoded in generative image and video models.

Bio:

Dor Verbin is a research scientist at Google DeepMind in San Francisco, where he works on computer vision, computer graphics, and machine learning. He received his Ph.D. in computer science from Harvard University. Previously, he received a double B.Sc. in physics and in electrical engineering from Tel Aviv University, after which he worked as a researcher at Camerai, developing real-time computer vision algorithms for mobile devices. He received the Best Student Paper Honorable Mention award at CVPR 2022.

The corners problem is a classical problem in additive combinatorics. A corner is a triple of points (x,y), (x+d,y), (x,y+d). It can be viewed as a 2-dimensional analog of a (one-dimensional) 3-term arithmetic progression. An old question of Ajtai and Szemeredi is: how many points can there be in the n x n integer grid without containing a corner? They proved a qualitative bound of o(n^2), but no effective quantitative bounds.

This question has an equivalent description in the language of communication complexity. Given 3 players with inputs x,y,z which are integers in the range 1 to n, what is the most efficient Number-On-Forehead (NOF) deterministic protocol to check if they sum to n. This connection was first observed in the seminal paper of Chandra, Furst and Lipton that introduced the NOF model back in 1983.

In the language of communication complexity, the trivial protocol sends log(n) bits, but there is a better NOF protocol (based on constructions in additive combinatorics) which only sends (log n)^{1/2} bits. However, the best lower bound until our work was double exponentially far off - of the order of log log log n. In this work, we close this gap, and prove a lower bound of (log n)^c for some absolute constant c.

The work is based on combining the high-level approach of Shkredov, who obtained the previous lower bound, which was based on Fourier analysis; with the recent breakthrough of Kelley and Meka on the 3-term arithmetic progression problem, and the ensuing developments. The main message is that "spreadness" based techniques (a notion that I will explain in the talk) give significantly better quantitative bounds compared to classical Fourier analysis.

Joint work with Michael Jaber, Yang P. Liu, Anthony Ostuni and Mehtaab Sawhney

Paper will appear in FOCS 2025
https://arxiv.org/abs/2504.07006

In some video understanding scenarios, it is important to capture details that exist at fine temporal resolution, over a significant length of context (hundreds, thousands and even tens of thousands of frames). This poses a computational challenge for many existing video encoders. I will discuss our recent efforts on developing models for video representation that address this challenge in two ways, each with a different kind of video task in mind. In our work on sign language understanding we extract information from each video frame in a highly selective way, and train the long context encoder from a large video corpus without any labels. The resulting video model, SHuBERT, is a "foundation model" for American Sign Language achieving state of the art performance on multiple sign language understanding tasks. In another, ongoing effort, we focus on the task of nonlinear movie editing, and develop an autoregressive model that relies on a highly compressed representation of video frames. This model, trained on an unlabeled corpus of movies, yields state of the art results on complex movie editing tasks and on editing-related video understanding benchmarks.

From rough sketches that spark ideas to polished illustrations that explain complex concepts, visual communication is central to how humans think, create, and share knowledge. Yet despite major advances in generative AI, we are still far from models that can reason and communicate through visual forms.

I will present my work on bridging generative models and visual communication, focusing on three complementary domains: (1) algorithms for generating and understanding sketches, (2) systems that support exploratory visual creation beyond one-shot generation, and (3) methods for producing editable, parametric images for design applications.

These domains pose unique challenges: they are inherently data-scarce and rely on representations that go beyond pixel-based images commonly used in standard models. I will show how the rich priors of vision-language models can be leveraged to address these challenges through novel optimization objectives and regularization techniques that connect their learned features with the specialized representations required for visual communication.

Looking ahead, this research lays the foundation for general-purpose visual communication technologies: intelligent systems that collaborate with humans in visual domains, enhancing how we design, learn, and exchange knowledge.

Bio:

Yael Vinker is a Postdoctoral Associate at MIT CSAIL, working with Prof. Antonio Torralba. She received her Ph.D. in Computer Science from Tel Aviv University, advised by Profs. Daniel Cohen-Or and Ariel Shamir. Her research spans computer graphics, computer vision, and machine learning, with a focus on generative models for visual communication. Her work has been recognized with two Best Paper Awards (SIGGRAPH 2022, SIGGRAPH Asia 2023) and a Best Paper Honorable Mention (SIGGRAPH 2023). She was selected as an MIT EECS Rising Star (2024) and received the Blavatnik Prize for Outstanding Israeli Doctoral Students in Computer Science (2024) as well as the VATAT Ph.D. Fellowship.