Public Session

8:00-8:30 AM
Check-in/Breakfast 

8:30-9:00 AM
Welcome and Year in Review 
 

Diana Marculescu
Founding Director, iMAGiNE Consortium and Professor, Chandra Family Department of Electrical and Computer Engineering 

9:00-9:45 AM
Keynote talk  

Advanced Technologies for Artificial Intelligence

AI is quickly changing the way we live. It will not only impact how the world uses technology but will affect us in ways that no other technology has previously. Although the AI era is still in its infancy, AI is already having a transformative impact across many industries by enabling automation of tasks, improved decision-making, scientific discoveries, and development of new products and services. In this talk, I will discuss some of the key technologies enabling rapid advancements in AI. I will also describe some major breakthroughs from AI applications and future directions for AI research.

Michael Schulte
Senior Fellow Design Engineer, AMD 

9:45-10:30 AM
Research highlights with iMAGiNE faculty and students

10:30-11:30 AM
Student Poster Session in Mulva Foyer, Level 0 (Light refreshments) 

Susana Alcorta
Lightweight ML-based Runtime Prefetcher Selection on Many-core Platforms

Agrim Bari
Managing Edge Offloading for Stochastic Workloads with Deadlines

James Boyle
SANA-FE: Simulating Advanced Neuromorphic Architectures for Fast Exploration

Hung-Yueh Chiang
SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Commodity Edge Devices

Yojan Chitkara
MaxMem: Colocation and Performance for Big Data Applications on Tiered Main Memory Servers

Geffen Cooper
Towards Machine Learning with Batteryless Sensors

Natalia Frumkin
Jumping through local minima: Quantization in the loss landscape of vision transformers

Anyesha Ghosh
Fast and Efficient Microservice Scaling with SurgeGuard

Junyuan Hong
Make Large Language Model Your Privacy-Preserving Prompt Engineer

Tianda Huang
Towards Machine Learning with Batteryless Sensors

Yeonsoo Jeon
Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning

Thomas Leonard
Shape-Dependent Multi-Weight Magnetic Artificial Synapses for Neuromorphic Computing
and
Magnetic Devices for Neuromorphic Edge Computing

Feng Liang
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

Shaohui Liu
Topology-aware GNNs for Learning Feasible and Adaptive ac-OPF Solutions

Mustafa Munir
GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs

Jaeyoung Park
PARLA: A programming system for heterogeneous computing

Souradip Poddar
A Data-Driven Analog Circuit Synthesizer with Automatic Topology Selection and Sizing

Vivian Rogers
Multi-state domain wall lattice racetrack memory devices utilizing Weyl magnetoresistance

Rishabh Sehgal 
Compute-MLROM: Compute-in-Multi Level Read Only Memory for Energy Efficient Edge AI Inference Engines

Sloke Shrestha
Leveraging Large Language Models to Annotate Activities of Daily Living Captured with Egocentric Vision

Zachary Susskind 
Differentiable Weightless Neural Networks

Endri Taka
MaxEVA: Maximizing the Efficiency of Matrix Multiplication on Versal AI Engine

Alice Zhang
Automated Face-to-Face Conversation Detection on a Commodity Smartwatch with Acoustic Sensing

Hanqing Zhu
Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accelerator

11:30 AM-12:45 PM
Panel discussion: “Interactive, Immersive AI from Cloud to Edge”
Featured Panelists:

Gustavo de Veciana
Professor, Chandra Family Department of Electrical and Computer Engineering

Radu Marculescu
Professor, Chandra Family Department of Electrical and Computer Engineering

Michael Schulte
Senior Fellow Design Engineer, AMD
 

Tauseef Rab
Engineering Manager, Meta
 

Private Session (Industry Members and Faculty Only):

12:45-1:45 PM
Lunch and Member meeting 

1:45-3:00 PM
Round Table Discussion  

3:00-3:30 PM
Closing Remarks/TBD

Parking validation will be provided in the San Jacinto parking garage. At check-in, please let us know you’ll need a parking QR code to exit the garage.
Complimentary wireless internet access for corporate guests is available at https://www.utguest.org/