ASSET Seminar: “Some Displaced Vignettes on Generalized Notions of Equivariance”
Abstract: The explicit incorporation of task-specific inductive biases through symmetry has emerged as a crucial design precept in the development of high-performance machine learning models. Symmetry-aware neural networks, such as […]
ASSET Seminar: “What’s In my Network? On Learned Proximals and Testing for Explanations”
Abstract: Modern machine learning methods are revolutionizing what we can do with data, from tiktok video recommendations to biomarkers discovery in cancer research. Yet, the complexity of these deep models […]
ASSET Seminar: “Advancing Diffusion Models for Text Generation”
Abstract: Transformer-based language models have undoubtedly become the dominant and favorite architecture for language generation of our time. However, although they provide impressive text quality, they tend to be hard […]
ASSET Seminar: “Wood Wide Models”
Abstract: Foundation models are monolithic models that are trained on a broad set of data, and which are then in principle fine-tuned to various specific tasks. But they are ill-suited […]
ASSET Seminar: “Towards Pluralistic Alignment: Foundations for Learning from Diverse Human Preferences”
Abstract: Large pre-trained models trained on internet-scale data are often not ready for safe deployment out-of-the-box. They are heavily fine-tuned and aligned using large quantities of human preference data, usually […]
ASSET Seminar: “Robustness in the Era of LLMs: Jailbreaking Attacks and Defenses”
Abstract: Despite efforts to align large language models (LLMs) with human intentions, popular LLMs such as chatGPT, Llama, Claude, and Gemini are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into […]
ASSET Seminar: “Representation-based Learning and Control for Dynamical Systems”
Abstract: The explosive growth of machine learning and data-driven methodologies have revolutionized numerous fields. Yet, the translation of these successes to the domain of dynamical physical systems remains a significant […]
ASSET Seminar: “Bridging the Gap Between Learning and Programming”
Abstract: For decades, we have built software by writing code, but in recent years machine learning has emerged as a new approach to create software with features that would be […]
IC2S2 Conference Virtual Keynote: “Societies are complex systems. So, how to manage them?”
To kick off the IC2S2 conference being held right here at the University of Pennsylvania, we warmly invite you to join us for Dirk Helbing’s (ETH Zurich) Virtual Keynote address […]
infoLeNS Seminar: “Emerging computational imaging inverse problems: from theory to algorithms”
In this talk, I will focus on two challenging imaging systems: snapshot compressive imaging and coherent imaging under speckle noise interference. I will begin by reviewing the core mathematical modeling […]