Computer Science seminars
September 2026
What Can Hardware Do for Computer Security?
Srini Devadas· Massachusetts Institute of Technology
Thu, Sep 24 · 23:00 UTC · Cambridge, MA · Hybrid
Srini Devadas examines how hardware and cryptography can strengthen each other. Hardware can protect keys, monitor attacks in real time and reduce the trusted computing base, while hardware vulnerabilities can undermine software security. The talk presents research on accelerating cryptographic computation and using those capabilities to design more efficient protocols. It also asks how cryptography and new security definitions can guide the construction of secure hardware. Devadas is MIT's Webster Professor of Electrical Engineering and Computer Science. Hybrid: MIT Stata Center, Room 32-G449 (Kiva), 32 Vassar Street, Cambridge, MA 02139; online via Zoom. Thursday 24 September 2026, talk at 19:00 EDT (UTC−4); in-person refreshments begin at 18:30. This public event is organized by the Boston Chapter of the IEEE Computer Society and GBC/ACM. Register through the organizer-linked Zoom form for either mode and indicate online or in-person attendance. For physical access, use the Stata Center entrance nearest Main Street, then the fourth-floor elevators.
Computer EngineeringCryptography+1 more
October 2026
Big Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI
Zohar Ringel· Hebrew University of Jerusalem
Wed, Oct 7 · 18:00 UTC
Deep networks are often thought of as black boxes. Their ability to encompass vast swathes of knowledge indeed makes them hard to explain. Yet many of their behaviours — generalization under overparametrization, grokking, OOD failures, neural scaling laws — recur across architectures and scales, and each, however surprising, can be reproduced and explained in controlled settings. I will review these efforts to identify and explain the universal phenomena of deep learning, and suggest that an LLM may amount to a sum of such tractable sub-phenomena, interpolative in nature. Finally, leaving scientific rigor aside, I'll argue that what separates this prosaic picture from the apparent magic of LLMs may well be the industrial scale of compute and human labour behind it, and that AGI in its deeper extrapolative sense may be much further away than claimed.
AIML+2 more
Recent recordings
5 past seminars in the archiveSWEBAGS conference 2022
Nicolas Trisch· New York University School of Medicine
Wed, Nov 30, 2022 · 13:00 UTC
SWEBAGS conference 2022
Stephanie Cragg· University of Oxford
Wed, Nov 30, 2022 · 09:00 UTC
Dissecting subcircuits underlying hippocampal function
Liset M. de la Prida· Instituto Cajal - CSIC
Wed, May 4, 2022 · 06:15 UTC
Liset M de la Prida is a Physicist (1994) and PhD in Neuroscience (1998), who leads the Laboratorio de Circuitos Neuronales at the Instituto Cajal, Madrid, Spain (http://www.hippo-circuitlab.es). The main focus of her lab is to understand the function of the hippocampal circuits in the normal and the diseased brain, in particular oscillations and neuronal representations. She is a leading international expert in the study of the basic mechanisms of physiological ripples and epileptic fast ripples, with strong visibility as developer of novel groundbreaking electrophysiological tools. Dr. de la Prida serves as an Editor for prestigious journals including eLife, Journal of Neuroscience Methods and eNeuro, and has commissioning duties in the American Epilepsy Society, FENS and the Spanish Society for Neurosciences.
NeuroePhys
SWEBAGS conference 2021
Aryn H. Gittis· Carnegie Mellon University
Fri, Dec 17, 2021 · 16:30 UTC
An Algorithmic Barrier to Neural Circuit Understanding
Venkat Ramaswamy· Birla Institute of Technology & Science
Fri, Oct 2, 2020 · 15:00 UTC
Neuroscience is witnessing extraordinary progress in experimental techniques, especially at the neural circuit level. These advances are largely aimed at enabling us to understand precisely how neural circuit computations mechanistically cause behavior. Establishing this type of causal understanding will require multiple perturbational (e.g optogenetic) experiments. It has been unclear exactly how many such experiments are needed and how this number scales with the size of the nervous system in question. Here, using techniques from Theoretical Computer Science, we prove that establishing the most extensive notions of understanding need exponentially-many experiments in the number of neurons, in many cases, unless a widely-posited hypothesis about computation is false (i.e. unless P = NP). Furthermore, using data and estimates, we demonstrate that the feasible experimental regime is typically one where the number of experiments performable scales sub-linearly in the number of neurons in the nervous system. This remarkable gulf between the worst-case and the feasible suggests an algorithmic barrier to such an understanding. Determining which notions of understanding are algorithmically tractable to establish in what contexts, thus, becomes an important new direction for investigation. TL; DR: Non-existence of tractable algorithms for neural circuit interrogation could pose a barrier to comprehensively understanding how neural circuits cause behavior. Preprint: https://biorxiv.org/content/10.1101/639724v1/…
NeuroComp NeuroVideo