Upcoming
-
Reinforcement Learning for Micro-architectural Attack and Defense (Nov 14)
Speaker: Mulong Luo | Date: Nov 14, 2:15 PM – 3:05 PM | Abstract: Securing modern computer systems against an ever-evolving threat like micro-architectural attacks is a significant challenge that requires innovative approaches…
Past
-
Haphazardness in LLMs and Its Implications for Agentic AI Systems (Nov 7)
Speaker: Xiuwen Liu | Date: Nov 7, 2:15 – 3:05 pm | Abstract: As large language models (LLMs) are increasingly deployed in agentic AI systems to iteratively solve complex tasks, empirical studies have revealed a persistent lack of reproducibility and…
-
Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration (Nov 4)
Speaker: Lin Jiang Date: Nov 4, 11:45 AM – 12:45 PM Abstract: The increasing frequency of extreme weather events, such as hurricanes, highlights the gent need for efficient and equitable power system restoration. Many electricity providers make restoration decisions primarily…
-
!!Cancelled!! Advancing Societal Decision-making through Human-AI Collaboration (Oct 31)
Speaker: Yifang Wang Date: Oct 31, 2:15 – 3:05 pm Abstract: Societal decision-making involves high-stakes, long-term choices that shape the future of communities, nations, and human collectives…
-
SOMA: Efficient Multi-turn LLM Serving via Small Language Model (Oct 28)
Speaker: Xueqi Cheng Date: Oct 28, 11:45 am – 12:45 pm Abstract: Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential…
-
A Unified Neural Operator Framework for Scalable Multi-Physics Simulations (Oct 24)
Speaker: Shibo Li Date: Oct 24, 2:15pm – 3:05 pm Abstract: Physical simulations are essential tools across critical fields such as mechanical and aerospace engineering, chemistry, meteorology, etc…
-
CREDIT: Certified Defense of Deep Neural Networks against Model Extraction Attacks (Oct 21)
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)
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…
-
Challenges in Bringing AI to Next Generation Edge Networks: A Physical Layer Perspective (Oct 10th)
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)
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,…
-
Model Extraction Attack and Defense for Large Language Models (Oct 7th)
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…