Efficient AI

Efficient Deep Neural Network Inference with Near-Edge Accelerator Offload

Hao Liu, Ph.D. Student, Computer Science

Nov 11, 09:30 - 11:30

B2 R5220

edge computing Efficient AI accelerators multi-stage optimization algorithm distributed computing Distributed algorithms

This thesis develops efficient distributed inference strategies for deep neural networks that exploit near-edge accelerators through edge, near-edge, and cloud tier offloading, optimized model partitioning, and collaborative expert-based processing to achieve low-latency, energy-efficient, and accurate AI inference on resource-constrained edge systems.

Event Status: Cancelled | Towards Trustworthy Acceleration for AI Systems

Yuchen Yang, Assistant Professor, Privacy and Cybersecurity Informatics, The Pennsylvania State University (PSU)

Oct 22, 12:00 - 13:00

B4 R5209

Trustworthy AI Efficient AI accelerators trustworthy machine learning privacy-preserving AI Security and Privacy secure AI secure system design

In this talk, I will show how inference acceleration can not only weaken safety and security but also become a tool for attackers, and how these findings guide secure system design.

Liangyu Wang

Ph.D. Student, Computer Science

LLM efficient deep learning architectures Reinforcement Learning Efficient AI privacy-preserving AI

Liangyu Wang's research focuses on efficient systems and optimization for large language models, including distributed training and inference, GPU systems, zeroth-order optimization, privacy-preserving training, and matrix-based optimizers.

The Three Pillars of Practical Machine Learning

Hasan Abed Al Kader Hammoud, Ph.D. Student, Electrical and Computer Engineering

Jun 16, 14:00 - 16:00

Zoom Meeting 98734301189

AI Trustworthy AI trustworthy machine learning Efficient AI adaptive methods

This thesis establishes methods, evaluation protocols, and insights toward machine learning systems that are practical, adaptive, efficient, and trustworthy paving path for practical machine learning that rests on key three pillars: adaptation, efficiency, and trustworthiness.

Kuilian Yang

Ph.D. Student, Electrical and Computer Engineering

High Performance Low Power Circuits noise-shaping differential SAR capacitance-digital converter neuromorphic computing Hardware acceleration Efficient AI edge computing low-latency architecture

Hasan Abed Al Kader Hammoud

Ph.D. Student, Electrical and Computer Engineering

Trustworthy AI Efficient AI AI Deep learning machine learning Computer Vision efficient adaptation LLM

Hao Liu

Ph.D. Student, Computer Science

edge computing Efficient AI deep neural networks LLM cloud technologies distributed computing Distributed algorithms distributed deep learning multi-stage optimization algorithm

Hao Liu is a Ph.D. candidate in Computer Science at King Abdullah University of Science and Technology (KAUST), advised by Prof. Suhaib Fahmy, where his research focuses on efficient deep neural network inference, edge and near-edge AI acceleration, distributed computing, and optimization techniques for low-latency, energy-efficient intelligent systems.

Charalampos Antoniadis

Research Scientist, Electrical and Computer Engineering

Efficient AI Generative AI and LLMs Electronic Design Automation Smart Cities