CS Colloquium
(R?)evolution Times. Prof. Moshe Tennenholtz (Technion)
Building 216 room 201Prof. Moshe Tennenholtz, Technion Will lecture on: (R?)evolution Times Recent years have shown dramatic progress in AI. Deep learning approaches employing the so-called "foundational models" are shaking the grounds of technology allowing for innovative products and services at quite an amazing speed. Criticisms and failures of these approaches have been considered: the need to incorporate ... Read more
Party Tricks: On Primaries and Gerrymandering. Omer Lev (BGU)
CS colloquium lecture by Dr. Omer Lev from Ben-Gurion University. Title: Party Tricks: On Primaries and Gerrymandering Abstract: In the last few years, the effects that primaries and gerrymandering have on election outcomes became a commonly debated issue, particularly in the US. Both primaries (candidate selection by parties) and district-based elections are examples of mechanisms that involve adding stages to a decison-making ... Read more
Generalization in Deep Learning Through the Lens of Implicit Rank Minimization. Nadav Cohen (TAU).
Building 216 room 201CS colloquium lecture will be given by Dr. Nadav Cohen from Tel-Aviv University. Title: Generalization in Deep Learning Through the Lens of Implicit Rank Minimization Abstract: Understanding deep learning calls for addressing three fundamental questions: expressiveness, optimization and generalization. Expressiveness refers to the ability of compactly sized neural networks to represent functions capable of solving real-world ... Read more
TAU Style: inversion, editing, and applications of StyleGAN. Dr. Amit Bermano from Tel-Aviv University (CS Colloquium)
Building 216 room 201(CS Colloquium) TAU Style: inversion, editing, and applications of StyleGAN. Dr. Amit Bermano Tel-Aviv University Abstract: The generative abilities of GANs are revolutionizing the field of image synthesis and manipulation. Specifically, StyleGAN reaches the highest levels of image quality, and has become the de-facto golden standard for the editing of facial images. StyleGAN is unsupervised, ... Read more
Recovering Data Semantics. Dr. Roee Shraga (CS Colloquium)
Building 203 Room 221Sunday, December 4, 2022 11:00 A.M. Building 203 Room 221 Dr. Roee Shraga Northeastern University in Boston י רצ ה על Will lecture on Recovering Data Semantics In data science, it is increasingly the case that the main challenge is finding, curating, and understanding the data that is available to solve a problem at hand. ... Read more
Prof. Gal Chechik Bar-Ilan University: Learning with visual foundation models for Gen AI
CS Auditorium (Bldg. 503)On May 23, Prof. Gal Chechik Bar-Ilan University will give a lecture on: Learning with visual foundation models for Gen AI Abstract: Between training and inference, lies a growing class of AI problems that involve fast optimization of a pre-trained model for a specific inference task. These are not pure “feed-forward” inference problems applied to ... Read more