6 papers
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Shreyas Rajesh, Kartik Sharma, Tonmoy Monsoor +8
Specialist epilepsy expertise is scarce in resource-constrained settings, making LLM-based decision support attractive for frontline clinicians managing longitudinal treatment. Suc…
Explainable deep learning improves human mental models of self-driving cars
Eoin M. Kenny, Akshay Dharmavaram, Sang Uk Lee +6
Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging to accurately anticipate when…
Panini: Continual Learning in Token Space via Structured Memory
Shreyas Rajesh, Pavan Holur, Mehmet Yigit Turali +2
Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retri…
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Shreyas Rajesh, Pavan Holur, Chenda Duan +2
Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degra…
Customizing Open Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems
Zhe Fei, Mehmet Yigit Turali, Shreyas Rajesh +7
Harmonizing medication data across Electronic Health Record (EHR) systems is a persistent barrier to monitoring medications for opioid use disorder (MOUD). In heterogeneous EHR sys…
Creating an AI Observer: Generative Semantic Workspaces
Pavan Holur, Shreyas Rajesh, David Chong +1
An experienced human Observer reading a document -- such as a crime report -- creates a succinct plot-like comprising different actors, their prototyp…