7 papers
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…
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…
Hierarchical Semantic Retrieval with Cobweb
Anant Gupta, Karthik Singaravadivelan, Zekun Wang
Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb…
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:…