Building Adaptable and Reliable AI with Probabilistic Modeling
Published: | 12:44 pm | Posted in: Events | Leave a comment
Speaker: Jake Snell
Date: Feb 19, 11:45am-12:45pm
Abstract: How can we build AI systems that produce more reliable outputs while consuming less data? In this talk, I will show how to answer this question by combining deep learning with tools from probabilistic modeling.
AI for Actionable Healthcare: Treatment Effect Estimation on Real-world Patient Data
Published: | 11:11 am | Posted in: Events | Leave a comment
Speaker: Ruoqi Liu
Date: Feb 17, 11:45am-12:45pm
Abstract: Estimating causal effects from observational data is a fundamental problem in many fields that face challenges (e.g., expensive, time-consuming, or even unethical) in running randomized control trials.
Towards Efficient, Dynamic, Portable Immersive Media
Published: | 11:00 am | Posted in: Events | Leave a comment
Speaker: Zhong Li
Date: Feb 14, 11:45am-12:45pm
Abstract: In the realm of immersive media, neural field-based methods have rapidly advanced in tasks such as 3D reconstruction and free-viewpoint rendering, achieving remarkable success in the fields of computer vision and graphics.
Understanding Microtargeting Pattern on Social Media
Published: | 9:48 am | Posted in: Events | Leave a comment
Speaker: Tunazzina Islam
Date: Feb 12, 11:45am-12:45pm
Abstract: The landscape of social media is highly dynamic, with users generating and consuming a diverse range of content. Various interest groups, including politicians, advertisers, and stakeholders, utilize these platforms to target potential users to advance their interests by adapting their messaging.
Robust and Interpretable Learning for Modern Healthcare
Published: | 2:01 pm | Posted in: Events | Leave a comment
Speaker: Peirong Liu
Date: Feb 10, 11:45am-12:45pm
Abstract: The unprecedented advances of modern machine learning have unlocked the potential for faster and more accurate data-driven analysis.
Addressing Information Distortion via Knowledge-aware Language Modeling
Published: | 4:48 pm | Posted in: Events | Leave a comment
Speaker: Yuanyuan Lei
Date: Feb 7, 11:45am-12:45pm
Abstract: In the research of Natural Language Processing (NLP), language and information are deeply intertwined. However, human language can be subject to various forms of information distortion, ranging from intentional misinformation to unintentional bias.
Securing Computer Systems using AI Methods and for AI Applications
Published: | 11:38 am | Posted in: Events | Leave a comment
Speaker: Mulong Luo
Date: Jan 31, 11:45am-12:45pm
Abstract: Securing modern computer systems against an ever-evolving threat landscape is a significant challenge that requires innovative approaches. Recent developments in artificial intelligence (AI), such as large language models (LLMs) and reinforcement learning (RL), have achieved unprecedented success in everyday applications.
Secure and Timely Execution in Cyber-physical Systems
Published: | 12:16 pm | Posted in: Events | Leave a comment
Speaker: Jinwen Wang
Date: Jan 15, 11:45am-12:45pm
Abstract: Cyber-physical systems (CPSs), such as self-driving cars, are integral to modern life. Execution timing is critical to CPS, as missing a deadline can result in severe outcomes. In this talk, I will present my work on guaranteeing execution timing in CPS security.
Towards Secure and Resilient Real-Time Cyber-Physical Systems
Published: | 11:12 am | Posted in: Events
Speaker: Abdullah Al Arafat Date: Jan 13, 11:45am-12:45pm Abstract: Recent advances in sensing, communication, and computing have revolutionized the accessibility and integration of safety-critical Cyber-Physical Systems (CPS). However, these systems face stringent timing constraints and escalating security challenges.
Towards Efficient and Practical Privacy-Preserving Computing and AI
Published: | 10:03 pm | Posted in: Events
Speaker: Qian Lou Date: Nov 22, 2:05pm – 3:15pm Abstract: With growing reliance on cloud-based Machine Learning as a Service (MLaaS), privacy concerns are escalating, particularly in fields like healthcare and finance. For instance, clinicians and researchers use AI models to analyze electronic health records for insights into conditions such as depression and Alzheimer’s disease. […]