Sai Praneeth Karimireddy

Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering

f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness

Do Data Valuations Make Good Data Prices?

Entropy-driven Fair and Effective Federated Learning

Conformal Prediction Adaptive to Unknown Subpopulation Shifts

OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Entropy-Based Aggregation for Fair and Effective Federated Learning

A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning

A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning

Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum