Amin Karbasi

Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback

On Union-Closedness of Language Generation

Procurement Auctions via Approximately Optimal Submodular Optimization

Intelligence at the Edge of Chaos

Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents

ClusterGen: Token Generation in Sublinear Time and Memory with Clustering KV Cache

Criteria and Bias of Parameterized Linear Regression under Edge of Stability Regime

(Im)possibility of Automated Hallucination Detection in Large Language Models

Adversarial Reasoning at Jailbreaking Time

Cognitive Overload Attack: Prompt Injection for Long Context

FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks