Invitation to AI Interpretability Seminars + AI Interpretability @ Illinois Spring 2026 Hiring Cycle Now Open
Apr 6, 2026 4:30 - 5:30 pm
0216 Siebel Center for Computer Science

- Sponsor
- AI Interpretability @ Illinois
- Speaker
- Xiaocong Yang
- Registration
- Registration
- ai-interpretability@illinois.edu
- Originating Calendar
- Illinois ECE Calendar
- Members of the ECE community are invited to an upcoming seminar on AI Interpretability — and, if you're curious to go deeper, to connect with our research team behind it.Seminar: A Unified Framework of AI Interpretability in the LLM Era: Architectures, Behaviors and BeyondMondays March 30 & April 6, 4:30–5:30pm | 0216 Siebel Center for Computer Science & ZoomIn the upcoming seminar, Xiaocong (CS Ph.D. candidate and founder of AI Interpretability @ Illinois) will present a unified framework of AI Interpretability covering:- Interpretable model architectures — post-hoc interpretability, white-box models, and generative interpretability- Interpretable emergent behaviors — how complex, high-level capabilities arise from simple, low-level training objectives- Structure–functionality correlations — how model structures and functionalities are co-determined as in biological intelligent systems- Implications for model safety & trustworthiness — how interpretability techniques can help audit and intervene in model behaviorsMissed the March 30 session? The recording is now available:We will be featuring discussion sessions during the seminar, as we encourage you to explore important open questions in this cutting-edge AI area together. For additional lecture recordings and slides from last semester, please visit our website: https://interpretability.web.illinois.edu/tutorial-materials/Join us on Monday April 6 in person at 0216 Siebel Center for Computer Science or via Zoom:----------------------------------------------------------------------------------------------------------------------------------------------------------About AI Interpretability @ IllinoisThis seminar is organized by AI Interpretability @ Illinois, a cross-lab research initiative dedicated to developing interpretable and scientifically grounded AI systems, as a part of CS 591 BAI Spring 2026. Our team is advised by renowned faculty members across Computer Science, ECE, Neuroscience, and Education on campus, and brings together passionate student researchers to share, brainstorm and collaborate on solving key problems in AI interpretability.We welcome anyone in the ECE community to reach out — whether you're looking to attend the seminars, meet our team members and get to know our ongoing research projects, explore collaborations or join our dynamic research team (please fill out the short interest form for joining our team at Spring 2026 cycle: https://forms.gle/Cs1wu4wCfApovvNm7).We look forward to seeing you soon!Xiaocong YangPh.D. Student, Computer Science, University of Illinois Urbana-Champaign
Founder, AI Interpretability @ Illinois