Dhanajit Brahma

Preprint · May 28, 2026 Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and storage than on principled write-side control. We frame memory evolution as a n ... Link to item Cite

A Probabilistic Framework for Lifelong Test-Time Adaptation

Preprint · December 19, 2022 Link to item Cite

Hypernetworks for Continual Semi-Supervised Learning

Preprint · October 5, 2021 Link to item Cite

Deep Attentive Ranking Networks for Learning to Order Sentences

Preprint · December 31, 2019 Link to item Cite

A Meta-Learning Framework for Generalized Zero-Shot Learning

Preprint · September 10, 2019 Link to item Cite