Marco Alvarez, Transforming Research and Higher Education with Generative AI and Foundation Models

When: Friday April 5. – noon-1 p.m. Where: Bliss 190 This talk delves into the transformative potential of generative AI and foundation models in both scientific research and higher education. Foundation models represent a seismic shift in AI capabilities, empowering researchers to analyze data, generate hypotheses, and uncover knowledge with unprecedented efficiency. Trained on vast […]

Continue reading "Marco Alvarez, Transforming Research and Higher Education with Generative AI and Foundation Models"

Yuwen Gu, fastkqr: A Fast Algorithm for Kernel Quantile Regression

When: Friday, March 22, from 2:00 PM to 3:00 PM Where: ENGR 045 Abstract: Quantile regression is a powerful tool for robust and heterogeneous learning that has seen applications in a diverse range of applied areas. Its broader application, however, is often hindered by the substantial computational demands arising from the nonsmooth quantile loss function. […]

Continue reading "Yuwen Gu, fastkqr: A Fast Algorithm for Kernel Quantile Regression"

Caiwen Ding, Co-Designing Algorithms and Hardware for Efficient Machine Learning (ML): Advancing the Democratization of ML

When: Friday, March 8th, from 2:00 PM to 3:00 PM Where: ENGR 045 Abstract: The rapid deployment of ML has witnessed various challenges such as prolonged computation and high memory footprint on systems. In this talk, we will present several ML acceleration frameworks through algorithm-hardware co-design on various computing platforms. The first part presents a […]

Continue reading "Caiwen Ding, Co-Designing Algorithms and Hardware for Efficient Machine Learning (ML): Advancing the Democratization of ML"

Oana Ignat, Towards Language-Vision Models for Positive Societal Impact

When: Monday 2/19 from 1:00 to 2:00 PM Where: Tyler 055 Abstract: Solving complex real-world problems often requires AI models that can process information from multiple modalities, such as language and vision, which can align with the needs of people from diverse backgrounds. An effective AI model will not only learn how to interact with […]

Continue reading "Oana Ignat, Towards Language-Vision Models for Positive Societal Impact"

Kaleel Mahmood, On the Robustness of Vision Transformers to Adversarial Examples

When: Friday 2/16 from 10:00 to 11:00 AM Where: Ranger 202 Abstract: Machine learning has become ubiquitous, being deployed in a range for domains like self driving cars, medical imaging and face recognition. With this increased use of machine learning an important question arises, how secure are these systems? In this presentation we dive into […]

Continue reading "Kaleel Mahmood, On the Robustness of Vision Transformers to Adversarial Examples"

Taslima Akter, Designing Privacy Enhancing Technology for Blind and Low-Vision (BLV) People

WHen: Tuesday 2/13 from 1:00 to 2:00 PM. Where: Quinn 214 Abstract: Advancements in computer vision and machine learning have empowered Blind and Low-Vision (BLV) individuals through camera-based assistive applications. These systems, capable of recognizing objects, identifying colors, and reading text, provide independence to BLV users. However, the reliance on camera-based assistive systems introduces privacy […]

Continue reading "Taslima Akter, Designing Privacy Enhancing Technology for Blind and Low-Vision (BLV) People"

Gianluca Brero (Brown University), Stackelberg POMDP: A Reinforcement Learning Approach for Economic Design

When: Friday, Feb 2nd, from 2:00 PM to 3:00 PM Where: ENGR 045 Abstract: We introduce a reinforcement learning framework for economic platform design where the interaction between the platform designer and the participants is modeled as a Stackelberg game. In this game, the designer (leader) sets up the rules for the platform, while the […]

Continue reading "Gianluca Brero (Brown University), Stackelberg POMDP: A Reinforcement Learning Approach for Economic Design"

Kelum Gajamannage, Low-rank data imputation using Hadamard deep autoencoders, with applications to fragmented trajectory reconstruction of collective motion

When: Friday, October 13 at 4:00 pm. Where: Fascitelli 040 Abstract: Data imputation is an essential preprocessing step in statistical learning that is to be performed before any technical analysis is conducted on partially observed data. Data originating from natural phenomena is low-rank due to diverse natural dependencies that a low-rank technique should primarily emphasize […]

Continue reading "Kelum Gajamannage, Low-rank data imputation using Hadamard deep autoencoders, with applications to fragmented trajectory reconstruction of collective motion"

Antonios Argyriou, Passive Wireless Sensing: Implications on Privacy and Counter-Measures

When: Monday, October 30 at 1:00 pm. Where: Quinn 211. Who: Dr. Antonios Argyriou, Associate Professor, Department of Electrical and Computer Engineering, University of Thessaly, Greece. Abstract: Emitters of wireless signals are all around us 24/7. These wireless signals contain digital information that may be the target of different types of cyber security attacks. However, […]

Continue reading "Antonios Argyriou, Passive Wireless Sensing: Implications on Privacy and Counter-Measures"