Date: Friday, October 09, 2026
Time: 11:00 AM (talk begins)
Location: Zoom Koch Hall, NCSU Centennial Campus
Title: How to Build a (Personal) AI-Powered Autonomous Scientific Computing System A Demo of the NC State ASCEND System
Speaker: Paul Liu, North Carolina State University
Talk Posting: https://www.csc.ncsu.edu/research/seminars

This talk is part of the AI Research Seminar Series

Host: Dongkuan (DK) Xu, CSC
Zoom Meeting Information:
Zoom URL: https://ncsu.zoom.us/j/97688532096?pwd=bmy7Kf64eXHQa80KGBpuYa3yYU1v1M.1
Zoom Meeting ID: 976 8853 2096
Zoom Passcode: 813477

Abstract:
What if your research computing worked like a conversation? You describe the experiment; an AI agent picks the right machine, writes the code, submits the jobs, watches them run, fixes what breaks, and reports back with results and provenance. In this talk, Dr. Liu, the Director of the NC State AI Hub for Science, will show live how to build exactly that on infrastructure already available at NC State, without a big team or a big budget: one person, a frontier coding agent, and a set of carefully designed guardrails.

Dr. Liu will demo ASCEND (Autonomous Scientific Computing Engine for Novel Discovery), an AI-powered working system that spans three very different NC State resources the NCShare GPU cluster, the Hazel HPC system, and a departmental single-GPU workstation. The demo will include a single 'front door' that probes live cluster state and uses AI to route each job to the right resource; agents that notice mid-conversation when they are on the wrong machine and suggest moving; one-command reproduction of published ML results; automated, policy-respecting retrieval of papers; and a knowledge base where the agent's lessons stay labeled as hypotheses until a real run validates them. The guiding principle: the agent reasons, but a controlled and auditable layer acts.

Along the way, Dr. Liu will share the recipes and hard-won gotchas multiplexing through Duo, shared-GPU etiquette, scheduler vs. no-scheduler boxes, onboarding new users from a single installer so attendees can leave with a blueprint for standing up their own personal autonomous computing assistant on university, industry or even your own resources.

Speaker Bio:
Paul Liu is a Professor in the Department of Marine, Earth and Atmospheric Sciences at North Carolina State University and Director of the College of Sciences AI Hub for Science. His research spans artificial intelligence for science and geoscience, with a particular focus on generative AI and large language models, AI agents, retrieval-augmented generation, and AI-enabled modeling of complex Earth and ocean systems. He has co-developed several domain-focused AI platforms, including OceanAI, OceanGPT, and DeltaGPT, and has led graduate courses and hands-on training programs on generative AI and LLMs for scientific research. His broader scientific work focuses on riverdeltacoastal systems, sediment transport, and large-scale environmental data modeling.

** Attention PhD Students **
Attendance at this seminar earns points toward your seminar requirement.
When attending a seminar via Zoom, *you must log in using your NC State credentials.* Otherwise you will not receive credit for attending the seminar.
In-person attendance will be verified using the new check-in tool (card reader).
Be there 10-15 mins before the talk starts and look for the student assistant to check in with your NC State ID.
Within 24 hours submit your seminar notes here https://webapps.csc.ncsu.edu/seminar_checkin/