Beyond LLMs: Neuro-Symbolic Approaches for Language Understanding
Abstract: Deep learning approaches to natural language processing (NLP), such as large language models (LLMs), have achieved tremendous success in recent years. However, these systems often "hallucinate" and can be difficult to understand, control, and maintain as needs evolve. In the first part of the talk, I will review these limitations and discuss how they affect the adoption of LLMs and other AI tools in important domains such as medical.
In the second part of the talk I will introduce several neuro-symbolic approaches developed in our lab that combine the strengths of both paradigms: the generalization power of neural methods and the flexibility of symbolic approaches. For example, in one of these approaches, we show that symbolic systems can guide the reasoning of LLMs in complex biomedical applications by highlighting which parts of the context are most relevant for understanding the underlying causal mechanisms. This simple strategy consistently improves LLM performance, in some cases doubling it.
Bio: Mihai Surdeanu is a Computer Science professor at the University of Arizona with courtesy appointments in Linguistics and Cognitive Science. Previously, he served as a research scientist at Stanford's NLP group and chief scientist at Lex Machina. His research focuses on systems that process and extract meaning from natural language texts, including question answering and information extraction, with an emphasis on interpretable models that can explain their decisions in human-understandable terms.
The AI-Defined Vehicle: Reshaping Mobility's Future
Abstract: We are witnessing a fundamental shift from software-assisted cars to truly "AI-defined" vehicles, where capabilities are no longer fixed but continuously evolve. The engine of this revolution is the transition to new, centralized compute platforms that enable AI models to run directly within the vehicle, powering everything from advanced perception to a completely redefined in-cabin experience. Generative AI and large language models are transforming driver assistance and the cockpit into a personalized, cooperative space. These developments are paving the way for a future ecosystem of highly adaptive, constantly learning, and deeply personal mobility solutions.
Bio: Victor Pankratius is Vice President for AI & Data at Bosch’s Cross-Domain Computing Solutions, shaping the next generation of AI systems for the physical world—from mobility and robotics to intelligent sensors. His work has driven Bosch’s domain-specific foundation models, advances AI-defined vehicles, and pioneers agentic AI architectures that bridge cloud intelligence and embedded systems. His career spans AI research and leadership at MIT, NASA, and Bosch, including his role as Global Head of Software at Bosch Sensortec, where he helped advance AI in mobile devices and wearables. Victor holds a Habilitation in Computer Science from Karlsruhe Institute of Technology and a doctorate from the University of Karlsruhe's business school.