CREDIT: Certified Defense of Deep Neural Networks against Model Extraction Attacks (Oct 21)
Published: | 7:54 am | Posted in: Events | Leave a comment
Speaker: Bolin Shen Date: Oct 21, 11:45 am – 12:45 pm Abstract: Machine Learning as a Service (MLaaS) has become a widely adopted method for delivering deep neural network (DNN) models, allowing users to conveniently access models via APIs…
UGAL-Q: A Multi-Agent Reinforcement Learning-Based Routing for Dragonfly Networks (Oct 17)
Published: | 7:50 am | Posted in: Events | Leave a comment
Speaker: Xin Yuan Date: Oct 17, 2:15 – 3:05 pm Abstract: Multi-Agent Reinforcement Learning (MARL)-based routing has emerged as a promising approach for high-performance interconnect networks such as Dragonfly, offering a viable alternative to the widely used Universal Globally Adaptive Load-balanced (UGAL) routing…
Challenges in Bringing AI to Next Generation Edge Networks: A Physical Layer Perspective (Oct 10th)
Published: | 12:33 pm | Posted in: Events | Leave a comment
Speaker: Xin Liu Date: Oct 10, 2:15 – 3:05 pm Abstract: The next generation of edge networks encompassing everything from IoT devices and smartphones to autonomous vehicles is poised to revolutionize industries by deploying AI in dynamic, real-world environments…
The Unwritten Curriculum: Lessons from a 25-Year Journey in Tech, Research, and AI (Oct 10th)
Published: | 10:27 am | Posted in: Events | Leave a comment
Speaker: Dr. Sanjay Agravat Date: Oct 10, 1:00pm – 2:00 pm Bio: Originally from Tallahassee, Florida, Dr. Sanjay Agravat is a Staff Software Engineer at Google with a 25-year career spanning academic research, teaching, and software engineering, residing in Atlanta, Georgia…
Model Extraction Attack and Defense for Large Language Models (Oct 7th)
Published: | 12:41 pm | Posted in: Events | Leave a comment
Speaker: Lican (Kelsey) Li Date: Oct 7, 11:45am – 12:45 pm Abstract: Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy…
A Distributed and Scalable Approach for Global Representation Learning with EHR Applications
Published: | 11:54 am | Posted in: Events | Leave a comment
Speaker: Zebin Wang Date: Sept 30, 11:45 am – 12:45 pm Abstract: Classical probabilistic graphical models face fundamental challenges in modern data environments, which are characterized by high dimensionality, source heterogeneity, and stringent data-sharing constraints.
Societally-Aware Autonomy: Games, Control, and Infrastructure for the Next Generation of Mobility Systems
Published: | 11:03 am | Posted in: Events | Leave a comment
Speaker: Ruolin Li Date: Sept 26, 2:15 – 3:05 pm Abstract: Autonomous vehicles (AVs) offer unprecedented opportunities to reshape transportation systems by enabling fine-grained control, real-time adaptability, and proactive system-wide coordination…
Dr. Grigory Fedyukovich has a paper accepted at OOPSLA
Published: | 7:42 am | Posted in: News | Leave a comment
Dr. Grigory Fedyukovich has a paper accepted at OOPSLA Dr. Grigory Fedyukovich has a paper accepted at the 2025 ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages & Applications (OOPSLA). The paper, titled “A Flow-Sensitive Refinement Type System for Verifying eBPF Programs”, is co-authored by PhD students Ameer Hamza and Lucas Zavalia. The paper presents […]
Dr. Shayok Chakraborty has a paper accepted at EMNLP 2025
Published: | 12:01 pm | Posted in: News | Leave a comment
Dr. Shayok Chakraborty has a paper accepted at EMNLP 2025 Dr. Shayok Chakraborty has a paper accepted at the Empirical Methods in Natural Language Processing (EMNLP) Findings 2025, a top tier conference in NLP. The paper is titled “MediVLM: A Vision Language Model for Radiology Report Generation from Medical Images”. All the authors of this […]
Unleashing the Power of Graph-Based Machine Learning as a Service
Published: | 8:01 am | Posted in: Events | Leave a comment
Speaker: Yushun Dong
Date: Sep 5, 2:15 – 3:05 pm
Abstract: The exponential growth of graph-structured data has created an unprecedented demand for graph learning capabilities across industries, yet domain experts face formidable barriers: massive computational requirements, prohibitive model costs, and complex infrastructure management.