The Rising Stars Award in MIT's Department of Brain and Cognitive Sciences (BCS) is awarded to 3 postdoctoral scholars per year. Recipients are awarded based on their outstanding research accomplishments and their extraordinary potential to succeed as independent research faculty. This award also aims to enhance diversity and representation in the brain and cognitive sciences. Awardees receive a cash prize and are invited to present their research in the BCS Colloquium Series.

Title: Control Systems for Speech, Language, and Intelligence

Speaker: Carmeen Amo Alonso

Abstract: Control theory is fundamental in the design and understanding of many natural and engineered systems, from cars and robots to power networks and bacterial metabolism. In the context of the brain, one of the most prominent application of control theory is the field of motor control. In this talk, we explore how the principles of control —formalized with control theory— have a much broader set of applications in neuroscience, cognitive science, and intelligent behavior. We focus on language applications, particularly language processing and grounding in technology, as well as speech processing in the human brain. We discuss three applications that exemplify the importance of control across a broad range of settings and research questions. First, we discuss how to leverage language embeddings with control to ground natural language commands in robot actions. We demonstrate how, using these insights, natural language commands can be used to directly instruct a robotic arm to perform a wide range of tasks while preserving safety guarantees. Then, we illustrate how control-theoretic principles can be used to steer the generation of foundation models. We illustrate how, by actively controlling per-layer activations, it is possible to steer a language model away from toxic content, or towards personalized responses. We discuss the potential of this work in both enhancing language models during post-training and its connection to in-context learning, as well as implications for mechanistic interpretability of embedding spaces in the context of Natural Language Processing. Lastly, we present how control-theoretic models of the brain’s auditory-articulatory system can be used to explain existing experimental results in a unifying framework. 

Bio: Carmen Amo Alonso is a Schmidt Science Fellow affiliated with the Computer Science Department at Stanford University. Her research lies at the intersection of control theory, machine learning, and optimization, with a focus on understanding and improving language processing and generation in both humans and machines. Carmen’s work aims to uncover the control mechanisms underlying language processing and intelligence, and leverages control-theoretic principles to develop safer, more controllable AI technologies. At Stanford, Carmen was named an Emerson Consequential Scholar for the potential of her research to positively impact society. Prior to joining Stanford, she held a postdoctoral fellow position at the Artificial Intelligence Center at ETH Zurich. Carmen earned her Ph.D. in Control and Dynamical Systems from Caltech in 2023, where she was advised by Prof. John Doyle. Her thesis on the optimal control of distributed systems under local communication constraints was awarded the Milton and Francis Clauser Doctoral Prize, which recognizes the best Ph.D. dissertation of the year across all disciplines at Caltech. During her Ph.D., her research received two best paper awards, was partially funded by Amazon and D. E. Shaw fellowships, and earned her the title of Rising Star in both EECS and Cyber-Physical Systems. Besides her research collaborations across academia and industry, Carmen is committed to education for all. As a member of Clubes de Ciencia, she travels to Mexico in the summer to teach underserved students.

Zoom: https://us02web.zoom.us/j/89002014229?pwd=bzZuZGh6cVhOSjJ6TlNZVHgrRnNaQT09

Followed by a reception with food and drink