Doctoral Thesis Proposal - Lingjing Kong
April 28, 2026 12:00PM—1:30PM
Location:
Newell-Simon Hall 3002
Speaker:
LINGJING KONG,
Ph.D. Student, Computer Science Department, Carnegie Mellon University
https://lingjing-kong.github.io/
Foundation models are rapidly becoming capable assistants for knowledge work, but their deployment in real settings is limited by three gaps: they do not transfer reliably across environments, their internal reasoning is opaque, and their behavior is hard to control precisely. In this talk, I argue that these limitations are not only about model size — they are fundamentally about whether learning captures and leverages the underlying structure of the data-generating process. I use causal thinking as a practical lens to model what is invariant, what changes, and what can be intervened on, and I further show how this leads to learning principles that improve trustworthiness. I will first present methods for learning unifying mechanisms from heterogeneous data, across domains and modalities, to enable reliable transfer and controllable generation. Next, I will show how structured concepts can be recovered even from seemingly unstructured data, by analyzing and improving self-supervised objectives (such as masking and diffusion) through hierarchical latent-variable models. These concept structures can then be used to interpret generative models and support targeted, multi-level edits. Finally, I connect these two threads to generalization beyond the training distribution. I will discuss natural conditions for extrapolation and a compositional generation framework that improves prompt following for novel concept combinations. I will conclude with a brief outlook on self-improving world models.
Thesis Committee:
Kun Zhang (Co-chair)
Yuejie Chi (Co-chair)
Eric Xing (Co-chair)
Tom Mitchell
Kevin Murphy (Google DeepMind)
In-person and Zoom
Contact
Matt Stewart