Integrated Calendar

In this talk we present a new approximate functional equation for the Hardy Z function with exponentially decaying error. This formula makes it possible to define a variation space for Z(t) consisting of a family of functions Z_N(t,a) with parameters a = (a1, …, aN) on a fixed window [2n, 2N + 2]. In this space the original Hardy function Z(t) is extremely well approximated in the window by the special choice a = (1, …, 1). Within this variation space we single out a natural domain RH_N in which all functions Z_N(t,a) have only real zeros in the window. We show that RH_N has striking connections with random matrix theory. In particular a Brownian motion with Skorokhod type reflection at the boundary of RH_N induces a Dyson Brownian motion in the \beta=2 case, and modern universality results then yield the expected GUE local statistics for elements of RH_N. No prior knowledge in number theory would be required.

Many fossil materials have embedded signals that enable aspects of the past to be reconstructed. These signals however can be altered or lost due to processes that take place once the fossil material is buried (diagenesis). Thus extracting reliable signals can be a major challenge. Here I present a new approach to better understanding diagenesis that I apply to bone.

The Dead Sea region has seen a rapid increase in sinkhole formation, posing serious environmental and infrastructure risks. The Geological Survey of Israel monitors sinkhole-related land subsidence along the western shore using InSAR, but current detection relies on manual interpretation of interferometric phase data, which is time-consuming and error-prone.In this talk, I present an AI-based Deep Learning framework for automated detection of sinkhole-related subsidence from InSAR data. The model learns interferometric phase deformation patterns, rather than visual features, and is trained using expert-labeled subsidence maps from years of operational monitoring. I demonstrate the model’s ability to generalize across spatial and temporal settings using multiple evaluation schemes and object-level performance metrics. Results show effective detection of subsidence areas, promising generalization to unseen regions, and the ability to reconstruct large-scale subsidence trends from patch-level predictions.

The field of artificial intelligence (AI) is undergoing a paradigm shift, moving from neural networks trained for narrowly defined tasks (e.g., image classification and machine translation) to general-purpose models such as ChatGPT. These models are trained at unprecedented scales to perform a wide range of tasks, from providing travel recommendations to solving Olympiad-level math problems. As they are increasingly adopted in society, a central challenge is to ensure the alignment of general-purpose models with human preferences. In this talk, I will present a series of works that reveal fundamental pitfalls in existing alignment methods. In particular, I will show that they can: (1) suffer from a flat objective landscape that hinders optimization, and (2) fail to reliably increase the likelihood of generating preferred outputs, sometimes even causing the model to generate outputs with an opposite meaning. Beyond characterizing these pitfalls, our theory provides quantitative measures for identifying when they occur, suggests preventative guidelines, and has led to the development of new data selection and alignment algorithms, validated at large scale in real-world settings. Our contributions address both efficiency challenges and safety risks that may arise in the alignment process. I will conclude with an outlook on future directions, toward building a practical theory in the age of general-purpose AI.

Short bio:

Noam Razin is a Postdoctoral Fellow at Princeton Language and Intelligence, Princeton University. His research focuses on the fundamentals of artificial intelligence (AI). By combining mathematical analyses with systematic experimentation, he aims to develop theories that shed light on how modern AI works, identify potential failures, and yield principled methods for improving efficiency, reliability, and performance.

Noam earned his PhD in Computer Science at Tel Aviv University, where he was advised by Nadav Cohen. Prior to that, he obtained a BSc in Computer Science (summa cum laude) at The Hebrew University of Jerusalem under the Amirim honors program. For his research, Noam received several honors and awards, including the Zuckerman Postdoctoral Scholarship, the Israeli Council for Higher Education (VATAT) Postdoctoral Scholarship, the Apple Scholars in AI/ML PhD fellowship, the Tel Aviv University Center for AI and Data Science excellence fellowship, and the Deutsch Prize for PhD candidates.

Microelectrode array (MEA) technology is routinely used to measure the physiological activity of electrogenic cells. We will present two novel high-density MEA (HD-MEA) systems designed for studying neural signals at high resolution, in networks and single cells. Additionally, we will highlight key applications, including neurocomputing, present relevant data and analysis techniques, and demonstrate how our HD-MEA technology advances the study of physiological processes in biological samples