Robert D Nowak

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds

Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench

Compress to Think, Decompress to Speak: Dual-Mode Reasoning in Transformers

Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks

Task Vectors in In-Context Learning: Emergence, Formation, and Benefits

Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation

SIEVE: General Purpose Data Filtering System Matching GPT-4o Accuracy at 1% the Cost

Unifying Generative and Dense Retrieval for Sequential Recommendation

Pretraining Decision Transformers with Reward Prediction for In-Context Structured Bandit Learning

DIRECT: Deep Active Learning under Imbalance and Label Noise