12 papers
Diffusion Models and Concept Formation
Zekun Wang, Karthik Singaravadivelan, Christopher J. MacLellan
Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the least cognitive…
Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
Zekun Wang, Anant Gupta, Zihan Dong +1
Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context windows expose more evidence,…
Test-Time Compositional Generalization in Diffusion Models via Concept Discovery
Zekun Wang, Anant Gupta, Tianyi Zhu +1
Compositional generalization requires models to produce novel configurations from familiar parts. In diffusion models, prior compositional generation methods typically assume that…
CobwebTM: Probabilistic Concept Formation for Lifelong and Hierarchical Topic Modeling
Karthik Singaravadivelan, Anant Gupta, Zekun Wang +1
Topic modeling seeks to uncover latent semantic structure in text corpora with minimal supervision. Neural approaches achieve strong performance but require extensive tuning and st…
A Rational Account of Categorization Based on Information Theory
Christopher J. MacLellan, Karthik Singaravadivelan, Xin Lian +2
We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how well it can account for key findings from…
Trust Region Continual Learning as an Implicit Meta-Learner
Zekun Wang, Anant Gupta, Christopher J. MacLellan
Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can ov…
AI Unplugged: Embodied Interactions for AI Literacy in Higher Education
Jennifer M. Reddig, Scott Moon, Kaitlyn Crutcher +1
As artificial intelligence (AI) becomes increasingly integrated into daily life, higher education must move beyond code-centric instruction to foster holistic AI literacy. We prese…
Grounded Concreteness: Human-Like Concreteness Sensitivity in Vision-Language Models
Aryan Roy, Zekun Wang, Christopher J. MacLellan
Do vision--language models (VLMs) develop more human-like sensitivity to linguistic concreteness than text-only large language models (LLMs) when both are evaluated with text-only…
Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
Nicki Barari, Edward Kim, Christopher MacLellan
Catastrophic forgetting remains a central challenge in continual learning, where models are required to integrate new knowledge over time without losing what they have previously l…
Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
Zekun Wang, Ethan Haarer, Tianyi Zhu +2
Inspired by the human ability to learn and organize knowledge into hierarchical taxonomies with prototypes, this paper addresses key limitations in current deep hierarchical cluste…
Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
Zekun Wang, Anant Gupta, Zihan Dong +1
Catastrophic forgetting remains a central obstacle for continual learning in neural models. Popular approaches -- replay and elastic weight consolidation (EWC) -- have limitations:…
Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
Zekun Wang, Ethan L. Haarer, Nicki Barari +1
We introduce the concept of a \textbf{neuro-symbolic pair} -- neural and symbolic approaches that are linked through a common knowledge representation. Next, we present \textbf{tax…