ASSET Seminar: “Demystifying the Inner Workings of Language Models”

Abstract: Large language models (LLMs) power a rapidly-growing and increasingly impactful suite of AI technologies. However, due to their scale and complexity, we lack a fundamental scientific understanding of much […]

ASSET Seminar: “Steering Machine Learning Ecosystems of Interacting Agents”

Abstract:  Modern machine learning models—such as LLMs and recommender systems—interact with humans, companies, and other models in a broader ecosystem. However, these multi-agent interactions often induce unintended ecosystem-level outcomes such […]

CIS Seminar: “Decentralized Mechanism Design: Cryptography Meets Game Theory”

In classical auction design, we take it for granted that the auctioneer is trusted and always implements the auction’s rules honestly. This assumption, however, no longer holds in modern auctions […]

CIS Seminar: “Generative Language Models for Biotherapeutics Design”

ASSET Seminar: “From Data to Insights: Trustworthy Solutions for Imaging Problems”

Abstract:  Extracting insights from imaging data used to be straightforward: every component of imaging systems was engineered by humans, the analysis and interpretation of the collected data was driven by […]

ASSET Seminar: “Poison and Cure: Non-Convex Optimization Techniques for Private Synthetic Data and Reconstruction Attacks”

Abstract: I will survey recent results describing the application of modern non-convex optimization methods to the problems of reconstruction attacks on private datasets (the “poison”), and the algorithmic generation of […]

ASSET Seminar: “Efficient Sharing of AI Infrastructures with Specialized Serverless Computing”

Abstract: The efficient sharing of AI infrastructures is becoming increasingly important in both public and private data centers. This demand is driven by two key factors: the proliferation of specialized […]

ASSET Seminar: Işil Dillig (University of Texas at Austin)

ASSET Seminar: Matt Frederickson (Carnegie Mellon University)

ASSET Seminar: “Getting Lost in ML Safety Vibes”

Abstract:  Machine learning applications are increasingly reliant on black-box pretrained models. To ensure safe use of these models, techniques such as unlearning, guardrails, and watermarking have been proposed to curb […]