BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//WP EVENT Manager Ical//NONSGML Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
DTSTART:19700101T000000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:6a03a035e3711@uvhere.com
DTSTAMP:20260512T214837Z
DTSTART;TZID=Asia/Kolkata:20260513T130000
DTEND;TZID=Asia/Kolkata:19700101T000000
LOCATION:Rm B12, ECSC (Conference Room)/ Online
SUMMARY:PhD Thesis Proposal: Mateusz Nowak
DESCRIPTION:“Less can be More and More can be Less: Strategic Data Utilization and The Consequences of Data Overload”ZOOM LINK Abstract: While machine learning has seen massive gains through large-scale data ingestion, the relationship between data volume, network architecture, and model reasoning remains underexplored. This thesis investigates the limitations of unstructured data scaling and demonstrates how targeted network design can enhance reasoning capabilities more effectively than sheer data volume. The research is structured into two main parts. First, we propose architectural modifications that allow models to better exploit intrinsic data structures without increasing dataset size. We demonstrate that tailoring architectures to the underlying data structure significantly improves performance on complex tasks, such as 3D reconstruction and world modeling. Second, we analyze the failure modes of high-capacity pre-trained models, quantifying how data overload degrades multiple-choice question understanding. We further examine how varying conceptual representations impact model performance across image and text modalities, focusing on image classification and sentiment analysis. Ultimately, this work provides a comprehensive framework for optimizing machine learning models through targeted augmentation and data-aware design, offering a structured evaluation of when ‘less can be more’ and ‘more can be less’ in the context of data scaling. Thesis Committee: Prof. Peter Chin (Chair), Prof. Xiaoyao Fan, Prof. Geoffrey P. Luke																										Email																																									Sponsored by: Thayer School of EngineeringSubscribe for event notifcations!Please enable JavaScript in your browser to complete this form.Please enable JavaScript in your browser to complete this form.Email Address *					Subscribe to Email							Subscribe to Event Notifications CategoriesArts and CultureCollege SportsFitness and OutdoorsFood and DrinkHoliday and SeasonalKids and FamilyLearning and WorkshopsMusic and NightlifeSubscribe
END:VEVENT
END:VCALENDAR