Events

Events Search and Views Navigation

Event Views Navigation

Today

  • Headshot of Dr. Yuejie Chi

    Optimization for ML and AI Seminar: Transformers Learn Generalizable Chain-of-Thought Reasoning via Gradient Descent

    HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

    Yuejie Chi, Yale Abstract: Transformers have demonstrated remarkable chain-of-thought reasoning capabilities, yet, the underlying mechanisms by which they acquire and extrapolate these capabilities remain limited. This talk presents a theoretical analysis of transformers trained via gradient descent for symbolic reasoning and state tracking tasks with increasing problem complexity. Our analysis reveals the coordination of multi-head […]

  • TILOS-SDSU ExpandAI Workshop

    Qualcomm Conference Center (Jacobs Hall first floor) 9736 Engineers Ln, La Jolla, CA, United States

    <!-- --> Agenda 1:00 – 1:10 pm: Welcome and opening remarks 1:10 – 1:30 pm: Invited talk by Dr. Lily Weng, Assistant Professor, Halıcıoğlu Data Science Institute and Department of Computer Science and Engineering, UC San Diego 1:30 - 1:50 pm: Invited talk by Dr. Reza Akhavian, Associate Professor and Jim Ryan Endowed Chair in Construction Engineering […]

  • TILOS-SDSU Seminar: Autopilots Need Parachutes: Reliability Lessons from LLM-Automated Embedded AI Systems

    Lamden Hall 341 (SDSU) and Virtual San Diego, CA, United States

    Roberto Morabito, EURECOM Abstract: Embedded AI systems are becoming increasingly complex to develop and maintain, requiring specialized workflows that span data processing, model conversion, optimization, and deployment across heterogeneous hardware platforms. Recently, large language models have emerged as a promising tool to automate parts of this lifecycle. In this talk, I present recent work investigating […]

  • Matus Telgarsky

    TILOS-Optimization for ML and AI Seminar: Implicit bias results for Muon, Adam, and Friends

    HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

    Matus Telgarsky, New York University Abstract: This talk will give both an empirical overview and a few simple bonds controlling the optimization path, or implicit bias, of modern optimization methods such as Adam and Muon (and Friends). The talk will begin with empirical results demonstrating the implicit bias phenomenon with shallow networks and also transformers […]

  • Headshot of Dr. Rene Vidal

    TILOS-HDSI Seminar: Engineering Interpretable and Faithful AI Systems

    HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

    René Vidal, University of Pennsylvania Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their growing deployment has exposed fundamental limitations in faithfulness, safety, and transparency. In this talk, I will present a unified perspective on addressing these challenges through principled model interventions […]

  • Headshot of Dr. Andre Wibisono

    Optimization for ML and AI Seminar: A survey of the mixing times of the Proximal Sampler algorithm

    HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

    Andre Wibisono, Yale University Abstract: Sampling is a fundamental algorithmic task with many connections to optimization. In this talk, we survey a recent algorithm for sampling known as the Proximal Sampler, which can be seen as a proximal discretization of the continuous-time Langevin dynamics, and achieves the current state-of-the-art iteration complexity for sampling in discrete […]

  • Aerial view of Rio de Janeiro, Brazil

    ICLR 2026 Workshop: Principled Design for Trustworthy AI – Interpretability, Robustness, and Safety across Modalities

    ICLR 2026 Riocentro Convention and Event Center, Rio de Janiero, Brazil

    Modern AI systems, particularly large language models, vision-language models, and deep vision networks, are increasingly deployed in high-stakes settings such as healthcare, autonomous driving, and legal decisions. Yet, their lack of transparency, fragility to distributional shifts between train/test environments, and representation misalignment in emerging tasks and data/feature modalities raise serious concerns about their trustworthiness. This […]

  • Headshot of Dr. Ellen Vitercik

    TILOS-HDSI Seminar with Ellen Vitercik (Stanford)

    HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

    Title and abstract TBA... Ellen Vitercik is an Assistant Professor at Stanford with a joint appointment between the Management Science and Engineering department and the Computer Science department. Her research interests include machine learning, algorithm design, discrete and combinatorial optimization, and the interface between economics and computation. Before joining Stanford, Dr. Vitercik was a Miller […]

  • Headshot of Dr. Tianyi Lin

    TILOS-HDSI Seminar: ComPO: Preference Alignment via Comparison Oracles

    HDSI 123 and Virtual 3234 Matthews Ln, La Jolla, CA, United States

    Tianyi Lin, Columbia University Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the likelihood displacement, which can be driven by noisy preference pairs that induce similar likelihood for preferred and dis-preferred responses. To address this issue, we consider doing derivative-free optimization based on […]