קולוקוויום וסמינרים

Protein sequences are abundant in repeating segments, both as exact copies and as approximate segments with mutations. These repeats are important for protein structure and function, motivating decades of algorithmic work on repeat identification. Recent work has shown that protein language models (PLMs) identify repeats, by examining their behavior in masked-token prediction.

To elucidate their internal mechanisms, we investigate how PLMs detect both exact and approximate repeats. We find that the mechanism for approximate repeats functionally subsumes that of exact repeats.

We then characterize this mechanism, revealing two main stages: PLMs first build feature representations using both general positional attention heads and biologically specialized components, such as neurons that encode amino-acid similarity. Then, induction heads attend to aligned tokens across repeated segments, promoting the correct answer.

Our results reveal how PLMs solve this biological task by combining language-based pattern matching with specialized biological knowledge, thereby establishing a basis for studying more complex evolutionary processes in PLMs.

The study of spectral graph determination is a central and fascinating topic in spectral graph theory and algebraic combinatorics. This area investigates the spectral characterization of various classes of graphs, develops methods for constructing and distinguishing cospectral nonisomorphic graphs, and analyzes the conditions under which the spectrum of a graph uniquely determines its structure. In the first part of the seminar, we present both classical results and recent advances in spectral graph determination.

The study of graph symmetries and different notions of transitivity is also of fundamental interest in algebraic graph theory. In the second part of the talk, we examine transitivity properties of Gilbert graphs and their complements, and discuss the main ideas underlying these results.

Powered prosthetic hands are frequently abandoned due to limited dexterity and unintuitive control. Most commercial devices rely on surface electromyography (sEMG) and support only grasping gestures, falling short of the fine, continuous finger motions required for everyday tasks such as typing on a keyboard or playing a musical instrument.

In this talk, we present a series of studies addressing this gap from three complementary angles. First, we introduce an end-to-end system that infers fine finger motions in real time by modeling the hand as a robotic manipulator and encoding muscle dynamics from ultrasound video. Second, we present a low-cost, 3D-printed prosthetic hand engineered for enhanced dexterity, featuring adjustable finger spacing, a two-degree-of-freedom wrist, and independent finger pressing. Third, we propose SonoRank, a step towards calibration-free finger flexion detection from forearm ultrasound.

SonoRank learns to rank ultrasound sequence pairs by relative motion magnitude, then fine-tunes using a rest reference to classify active flexion across all five fingers without user training data. Together, these papers advance prosthetic control toward practical, calibration-free deployment with fine-finger activation, bringing us closer to restoring native hand function for individuals with upper-limb amputation.

Consider a model in which we can access a parity function through random uniformly distributed labeled examples in the presence of random classification noise. In this thesis, we study learning in this model and show that approximating the number of relevant variables of a parity function is as hard as properly learning it.

More specifically, let $\gamma : \mathbb{R}^+ \to \mathbb{R}^+$ be any strictly increasing function satisfying $\gamma(x) \ge x$. In our first result, we show that from any polynomial-time algorithm that returns a $\gamma$-approximation $D$ (i.e., $\gamma^{-1}(d(f)) \leq D \leq \gamma(d(f))$), of the number of relevant variables~$d(f)$ of any parity function $f$, we can, in polynomial time, construct a solution to the long-standing open problem of polynomial-time learning $k(n)$-sparse parities (parities with $k(n)\le n$ relevant variables), where $k(n) = \omega_n(1)$.

In our second result, we show that from any $T(n)$-time algorithm that, for any parity $f$, returns a $\gamma$-approximation of the number of relevant variables $d(f)$ of $f$, we can, in polynomial time, construct a $poly(\Gamma(n))T(\Gamma(n)^2)$-time algorithm that properly learns parities, where $\Gamma(x)=\gamma(\gamma(x))$.

If $T(\Gamma(n)^2)=\exp({o(n/\log n)})$, this would resolve another long-standing open problem of properly learning parities in the presence of random classification noise in time~$\exp({o(n/\log n)})$.

Recent advances in computer vision, foundation models, and transformer architectures have transformed computational pathology, enabling deep learning systems to extract clinically actionable information directly from digitized tissue slides. This seminar explores how these technologies come together in modern digital pathology frameworks, and presents two studies demonstrating their clinical impact.

The first study addresses a critical diagnostic gap in low-resource settings, showing that convolutional neural networks applied to Giemsa-stained bone marrow aspirates can predict B/T-cell lineage and ETV6–RUNX1 translocation status in pediatric acute lymphoblastic leukemia — tasks that traditionally require expensive molecular assays unavailable in many parts of the world.

The second study tackles overtreatment in breast cancer. The TAILORx trial established that adjuvant chemotherapy can be spared for postmenopausal HR+/HER2− node-negative breast cancer patients with a 21-gene Recurrence Score (RS) of 11–25. However, among premenopausal women with RS 16–25, a small benefit from chemotherapy could not be ruled out. Consequently, guidelines suggest considering chemotherapy for this population, creating a therapeutic dilemma and leading to widespread overtreatment of patients who may not benefit from chemotherapy. Using deep survival analysis on H&E whole-slide images, we identify which women in this group truly benefit from adjuvant chemotherapy. Our model stratifies 76% of this population as low-risk, for whom chemotherapy can be safely omitted, while correctly identifying the high-risk subset that benefits from treatment.

Together, these works illustrate how digital pathology can democratize access to precision diagnostics and enable more personalized, less toxic cancer care.