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 of LLMs’ behavior, even when they are open source. The “black-box” nature of LMs not only complicates model debugging and evaluation, but also limits trust and usability. In this talk, I will describe how my research on interpretability (i.e., understanding models’ inner workings) has answered key scientific questions about how models operate. I will then demonstrate how deeper insights into LLMs’ behavior enable both 1) targeted performance improvements and 2) the production of transparent, trustworthy explanations for human users.

Bio: Sarah Wiegreffe is a postdoctoral researcher at the Allen Institute for AI (Ai2) and the Allen School of Computer Science and Engineering at the University of Washington. She has worked on the explainability and interpretability of neural networks for NLP since 2017, with a focus on understanding how language models make predictions in order to make them more transparent to human users. She has been honored as a 3-time Rising Star in EECS, Machine Learning, and Generative AI. She received her PhD in computer science from Georgia Tech in 2022, during which time she interned at Google and Ai2 and won the Ai2 outstanding intern award. She frequently serves on conference program committees, receiving outstanding area chair awards at ACL 2023 and EMNLP 2024.

To advance AI toward true artificial general intelligence, it is crucial to incorporate a wider range of sensory inputs, including physical interaction, spatial navigation, and social dynamics. However, achieving the successes of self-supervised Large Language Models (LLMs) across other modalities in our physical and digital environments remains a significant challenge. In this talk, I will discuss how self-supervised learning methods can be harnessed to advance multimodal models beyond the need for human supervision. Firstly, I will highlight a series of research efforts on self-supervised visual scene understanding that leverage the capabilities of self-supervised models to “segment anything” without the need for 1.1 billion labeled segmentation masks, unlike the popular supervised approach, the Segment Anything Model (SAM). Secondly, I will demonstrate how generative and understanding models can work together synergistically, allowing them to complement and enhance each other. Lastly, I will explore the increasingly important techniques for learning from unlabeled or imperfect data within the context of data-centric representation learning. All these research topics are unified by the same core idea: advancing multimodal models beyond human supervision.

Bio: XuDong Wang is a final-year Ph.D. student in the Berkeley AI Research (BAIR) lab at UC Berkeley, advised by Prof. Trevor Darrell, and a research scientist on the Llama Research team at GenAI, Meta. He was previously a researcher at Google DeepMind (GDM) and the International Computer Science Institute (ICSI), and a research intern at Meta’s Fundamental AI Research (FAIR) labs and Generative AI (GenAI) Research team. His research focuses on self-supervised learning, multimodal models, and machine learning, with an emphasis on developing foundational AI systems that go beyond the constraints of human supervision. By advancing self-supervised learning techniques for multimodal models—minimizing reliance on human-annotated data—he aims to build intelligent systems capable of understanding and interacting with their environment in ways that mirror, and potentially surpass, the complexity, adaptability, and richness of human intelligence. He is a recipient of the William Oldham Fellowship at UC Berkeley, awarded for outstanding graduate research in EECS.

Generative models have achieved remarkable quality and success in a variety of machine learning applications, promising to become the standard paradigm for regression. However, each predominant approach comes with drawbacks in terms of inference speed, sample quality, training stability, or flexibility. In this talk, I will propose Free-Form Flows, a new generative model that offers fast data generation at high quality and flexibility. I will guide you through the fundamentals and showcase a variety of scientific applications.

Bio: Felix Draxler is a Postdoctoral Researcher at the University of California, Irvine. His research focuses on the fundamentals of generative models, with the goal of making them not only accurate but also fast and versatile. He received his PhD in 2024 from Heidelberg University, Germany.

Since emerging in 2020, neural radiance fields (NeRFs) have marked a transformative breakthrough in representing photorealistic 3D scenes. In the years that followed, numerous variants have evolved, enhancing performance, enabling the capture of dynamic changes over time, and tackling challenges in large-scale environments. Among these, NVIDIA’s Instant-NGP stood out, earning recognition as one of TIME Magazine’s Best Inventions of 2022. Radiance fields now facilitate advanced 3D scene understanding, leveraging large language models (LLMs) and diffusion models to enable sophisticated scene editing and manipulation. Their applications span robotics, where they support planning, navigation, and manipulation. In autonomous driving, they serve as immersive simulation systems or can be used as digital twins for video compression integrated in edge computing architectures. This lecture explores the evolution, capabilities, and practical impact of radiance fields in these cutting-edge domains.

Bio: Matúš Dopiriak is a 3rd-year PhD candidate at the Technical University in Košice, Department of Computers and Informatics, advised by Professor Ing. Juraj Gazda, PhD. His research explores the integration of radiance fields in autonomous mobility within edge computing architectures. Additionally, he studies the application of Large Vision-Language Models (LVLMs) to address edge-case scenarios in traffic through simulations that generate and manage these uncommon and hazardous conditions.

Reinforcement learning is increasingly used to train robots for tasks where safety is critical, such as autonomous surgery and navigation. However, when combined with deep neural networks, these systems can become unpredictable and difficult to trust in contexts where even a single error is often unacceptable. This talk explores two complementary paths toward safer reinforcement learning: making agents more reliable through constrained training, and adding formal guarantees through techniques such as verification and shielding. In the second part of the talk, we will look at the growing role of world modeling in robotics and how this, together with the rise of large foundation models, opens up new challenges for ensuring safety in complex, real-world environments.

Bio: Davide Corsi is a postdoctoral researcher at the University of California, Irvine, where he works in the Intelligent Dynamics Lab led by Prof. Roy Fox. His research lies at the intersection of deep reinforcement learning and robotics, with a strong focus on ensuring that intelligent agents behave safely and reliably when deployed in real-world, safety-critical environments. He earned his PhD in Computer Science from the University of Verona under the supervision of Prof. Alessandro Farinelli, with a dissertation on safe deep reinforcement learning that explored both constrained policy optimization and formal verification techniques. During his PhD, he spent time as a visiting researcher at the Hebrew University of Jerusalem with Prof. Guy Katz, where he investigated the integration of neural network verification into learning-based control systems. Davide’s recent work also explores generative world models and causal reasoning to enable autonomous agents to predict long-term outcomes and safely adapt to new situations. His research has been published at leading venues such as AAAI, IJCAI, ICLR, IROS, and RLC, where he was recently recognized with an Outstanding Paper Award for his work on autonomous underwater navigation.

To be announced.

To be announced.

To be announced.