לוח שנה משולב

While neural networks revolutionized fields like computer vision and natural language processing, training them is time consuming and computationally demanding. Now, imagine that instead of training, one could simply search online for the most accurate model for their specific task and use it directly.  With more than 1.5 million public models available on HuggingFace, this is becoming feasible. However, retrieving the right model for each task is non-trivial, and the key technical challenge is designing meaningful representations of models themselves. To address this, we introduce ProbeLog, a probing-based approach for representing classification models from their weights. Then, by projecting CLIP text embeddings into this representation space we can enable zero-shot model retrieval.
 

Bio:
Jonathan is a Computer Science PhD student at The Hebrew University of Jerusalem, under the supervision of Prof. Yedid Hoshen.  Currently, He is working on weight space learning, aiming to understand what information can be extracted from pre-trained neural networks. His recent research can be viewed at https://pages.cs.huji.ac.il/jonkahana.

The well-known Zig-Zag product and related graph operators, like derandomized squaring, are fundamentally combinatorial in nature. Classical bounds on their behavior often rely on a mix of combinatorics and linear algebra. However, these traditional bounds are not tight and frequently fail to align with experimental results. In this talk, we will present a more refined analysis that utilizes the full spectrum of the graph, rather than relying solely on its spectral expansion. This approach produces results that both match experimental observations and, in a sense, are proved to be optimal. Our technique is analytic, diverging from classical methods: for the upper bound, we apply finite free probability, while for the lower bound, we draw on results from analytic combinatorics.
Based on joint works with Itay Cohen, Gal Maor and Yuval Peled. No prior knowledge is required.

I will show that every acylindrically hyperbolic group Γ admits a weakly mixing probability measure preserving action which is faithful but not essentially free. In other words, Γ admits a weakly mixing nontrivial faithful IRS. I will also show that every hyperbolic group admits a characteristic random subgroup with the same properties. Both results rely on works of Sun and Kechris–Quorning. 

This is a joint work with Anton Hase.

Let $\mathcal{R} : L^\infty(\mathbb{S}^{n-1}) \rightarrow L^\infty(\mathbb{S}^{n-1})$ denote the spherical Radon transform, defined as $\mathcal{R}(f)(\theta) = \int_{\mathbb{S}^{n-1} \cap \theta^{\perp}} f(u) d\sigma(u)$. A long-standing question in non-linear harmonic analysis due to Lutwak, Gardner, and Fish--Nazarov--Ryabogin--Zvavitch, is to characterize those non-negative $\rho \in L^\infty(\mathbb{S}^{n-1})$ so that $\mathcal{R}(\rho^{n-1}) = c \rho$ when $n\geq 3$. We show that this holds iff $\rho$ is constant, and moreover, $\mathcal{R}(\mathcal{R}(\rho^{n-1})^{n-1}) = c \rho$ iff $\rho$ is either identically zero or is the reciprocal of some Euclidean norm. Our proof recasts the problem in a geometric language using the intersection body operator $I$,  introduced by Lutwak following the work of Busemann, which plays a central role in the dual Brunn-Minkowski theory. We show that for any star-body $K$ in $\mathbb{R}^n$ when $n \geq 3$, $I^2 K = c K$ iff $K$ is a centered ellipsoid, and hence $I K = c K$ iff $K$ is a centered Euclidean ball. To this end, we interpret the iterated intersection body equation as an Euler-Lagrange equation for a certain volume functional under radial perturbations, derive new formulas for the volume of $I K$, and introduce a continuous version of Steiner symmetrization for Lipschitz star-bodies, which (surprisingly) yields a useful radial perturbation exactly when $n\geq 3$.

Joint work with Shahar Shabelman and Amir Yehudayoff.

I will explain the conjectured duality between double-scaled SYKat infinite temperature and the static patch of a particularversion of JT-de Sitter space. The conjectured duality raises thequestion of what particle physics is like in the bulk of the staticpatch.The answer: I will give it in the lecture.