Back to search

University of British Columbia

Building robust and adaptive foundation models using structured learning signals

Abstract

dc:description

Machine learning models are increasingly adapted in settings where supervision is incomplete, biased, or indirect, and where data distributions, tasks, and behavioral requirements evolve. In such regimes, optimizing the task objective alone often leads to spurious shortcut learning, catastrophic forgetting, or undesirable behavioral drift. This thesis studies how introducing additional structure into the learning process, beyond standard empirical risk minimization, enables more reliable model adaptation across vision and language domains. In visual recognition, the thesis develops structured representation learning methods that improve data efficiency, interpretability, and robustness. We introduce a weakly supervised framework for learning spatially grounded semantic representations via alignment and disentanglement regularization, improving few-shot generalization without requiring strong localization supervision. We further address incidental correlation learning in part-based models by explicitly separating foreground and background factors and enforcing invariance, thereby improving robustness to background shifts and domain perturbations. The thesis also proposes a replay-free continual object detection framework that mitigates catastrophic forgetting and prevents confusion between previously learned objects and the background during incremental updates. Finally, the thesis extends these principles to foundation model fine-tuning. It introduces an alignment-aware fine-tuning framework that incorporates feedback from external verification models through a policy-gradient–based regularization term, enabling control over behavioral properties such as safety and factuality while preserving task performance. Together, these contributions demonstrate that reliable adaptation requires learning signals beyond task loss, enabling robust, interpretable, and aligned models under distribution shift and repeated fine-tuning.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy - PhD
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Bhatt, Gaurav
Contributors dc:contributor
  • Sigal, Leonid

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/94492

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Bhatt, Gaurav. Building robust and adaptive foundation models using structured learning signals. doctoral thesis, University of British Columbia, 2026. http://hdl.handle.net/2429/94492