Hamed Hassani

Robust Decision-Making with Partially Calibrated Forecasters

Benchmarking Mitigations For Covert Misuse

BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks

Conformal Risk-Averse Decision Making with Action Conditional Guarantees

Human-AI Collaborative Uncertainty Quantification

Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization

Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective

Conformal Information Pursuit for Interactively Guiding Large Language Models

Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding

Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents

On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning

Adversarial Reasoning at Jailbreaking Time

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

Conformal Training with Reduced Variance

Watermark Smoothing Attacks against Language Models