Title: Perception/Control Co-Design for Autonomous Vehicles Speaker: Dr. Marilyn Wolf, University of Nebraska - Lincoln Date and Time: Monday, November 9, 2:00 pm Location: EH 2430 Abstract: Perception is a critical computational task in autonomous vehicles. Autonomous vehicles place stringent and somewhat conflicting demands on perception systems: high accuracy, low latency, and performance on limited […]
Title: From Domain-Specific Accelerators to Spatial Architecture Exploration Speaker: Dr. Jongeun Lee Date and Time: Thursday, July 30, 10:30am Location: ISEB 1310 Abstract: Emerging scientific and machine learning workloads increasingly benefit from domain-specific hardware accelerators, yet designing efficient architectures for these applications requires both effective implementations and scalable methods for architectural exploration. In this talk, […]
Title: Software-Defined Accelerator-Centric Systems - A Journey to AI and Big Data Acceleration Speaker: Dr. Zhenman Fang Date and Time: Wednesday, July 29, 11:00am Location: ISEB 4020 Abstract: With the end of CPU scaling due to dark silicon limitations, customizable hardware accelerators have gained increasing attention in modern datacenters and edge devices, due to their […]
Title: The Brave New (Quantum) World Speaker: Dr. Anupam Chattopadhyay Date and Time: Thursday, July 23, 10:00am Location: ISEB 1310 Abstract: Major advances across all the design stack of Quantum computing – algorithm, software, and hardware – has brought us to a realm where, it is impossible to ignore the effect of Quantum computing in […]
DATE/TIME: Friday, February 13, 10:30am
SPEAKER: Jooyoung Lee
This talk presents a solution to build on a dedicated combinatorial-optimization engine that directly models the search space rather than relying on proxy rewards, advancing AI that can reliably solve the hardest optimization problems in semiconductor design and beyond.
DATE/TIME: Tuesday, November 4, 2:00pm
SPEAKER: Dr. Prabha Sundaravadivel
This talk presents recent advances in low-cost embedded autonomy, where edge AI, sensor fusion, and adaptive control enable real-time decision-making within compact, power-efficient platforms.
DATE/TIME: Wednesday, October 15, 2:00pm
SPEAKER: Dr. Xulong Tang
I will discuss novel techniques such as lightweight invalidations for page translation, short-circuiting page table walks, and multi-instance GPU (MIG) reconfiguration strategies that collectively deliver substantial performance and efficiency gains to overcome these bottlenecks and unleash the full potential of multi-GPU computing.
DATE/TIME: Monday, June 9, 11:00am
SPEAKER: Mengyuan Li, Professor @ USC
I will share my insights into two real-world vulnerabilities we uncovered within commercial Confidential Computing systems, along with our joint efforts with CPU manufacturers to address these issues in the latest server-grade CPUs.
DATE/TIME: Monday, May 19, 11:00am
SPEAKER: Ziqi Zhang, Postdoc Researcher @ University of Illinois Urbane-Champaign
In this talk, I will introduce recent work on TEE-based LLM protection (TSLP) on the user devices: TEESlice (S&P24) and ArrowCloak (Security25 revision).
DATE/TIME: Monday, May 19, 11:00am
SPEAKER: Shaofei Li, Ph.D. @ Peking University
In this talk, I will present our novel approach, Query Provenance Analysis (QPA), for defending against query-based black-box attacks robustly (against both non-adaptive and adaptive attacks) and efficiently (in real-time).
DATE/TIME: Monday, April 21, 11:00am
SPEAKER: Yicheng Zhang, Ph.D. Candidate @ UC Riverside
To improve the performance and efficiency of modern computing systems, architects increasingly adopt heterogeneous designs that tightly integrate specialized accelerators such as GPUs and FPGAs. In this talk, I will present my research efforts to uncover and mitigate security vulnerabilities in these heterogeneous platforms.
DATE/TIME: Wednesday, March 12, 2:00pm
SPEAKER: Prof. Yu Bai, Intelligent Computing Research Lab @ CSU
This talk explores the challenges and innovations in optimizing AI efficiency, bridging algorithmic advancements and hardware design to enhance performance from inference to training.