Hamed Hassani

Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities ACL 2026 Watermark Smoothing Attacks against Language Models EMNLP 2025 Adaptively profiling models with task elicitation EMNLP 2025 Evaluating the Performance of Large Language Models via Debates NAACL 2025 Asymptotics of Linear Regression with Linearly Dependent Data L4DC 2025 Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing AACL 2025 On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning ICML 2025 Adversarial Reasoning at Jailbreaking Time ICML 2025 Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents ICML 2025 Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing IJCNLP 2025 Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding ICLR 2025 Adversarial Training Should Be Cast as a Non-Zero-Sum Game ICLR 2024 Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling AISTATS 2024 Uncertainty in Language Models: Assessment through Rank-Calibration EMNLP 2024 A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks ICML 2024 Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth ICML 2024 Conformal Prediction with Learned Features ICML 2024 Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks ICML 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NIPS 2024 One-Shot Safety Alignment for Large Language Models via Optimal Dualization NIPS 2024 Length Optimization in Conformal Prediction NIPS 2024 Linear Stochastic Bandits over a Bit-Constrained Channel L4DC 2023 Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods ICML 2023 Demystifying Disagreement-on-the-Line in High Dimensions ICML 2023 T-Cal: An Optimal Test for the Calibration of Predictive Models JMLR 2023 Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning ICLR 2023 Self-Consistency of the Fokker Planck Equation COLT 2022 FedAvg with Fine Tuning: Local Updates Lead to Representation Learning NIPS 2022 Probable Domain Generalization via Quantile Risk Minimization NIPS 2022 Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds NIPS 2022 Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints NIPS 2022 Minimax Optimization: The Case of Convex-Submodular AISTATS 2022 Federated Functional Gradient Boosting AISTATS 2022 An Agnostic Approach to Federated Learning with Class Imbalance ICLR 2022 Do deep networks transfer invariances across classes? ICLR 2022 Probabilistically Robust Learning: Balancing Average and Worst-case Performance ICML 2022 Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients NIPS 2021 Model-Based Domain Generalization NIPS 2021 Exploiting Shared Representations for Personalized Federated Learning ICML 2021 Optimal Algorithms for Submodular Maximization with Distributed Constraints L4DC 2021 Adversarial Robustness with Semi-Infinite Constrained Learning NIPS 2021 One Sample Stochastic Frank-Wolfe AISTATS 2020 FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization AISTATS 2020 Black Box Submodular Maximization: Discrete and Continuous Settings AISTATS 2020 Quantized Decentralized Stochastic Learning over Directed Graphs ICML 2020 Submodular Meta-Learning NIPS 2020 Sinkhorn Natural Gradient for Generative Models NIPS 2020 Sinkhorn Barycenter via Functional Gradient Descent NIPS 2020 Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization JMLR 2020 Precise Tradeoffs in Adversarial Training for Linear Regression COLT 2020 Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free AISTATS 2020 Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback NIPS 2019 Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks NIPS 2019 Hessian Aided Policy Gradient ICML 2019 Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match NIPS 2019 Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs ICML 2019 Robust and Communication-Efficient Collaborative Learning NIPS 2019 Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity ICML 2018 Online Continuous Submodular Maximization AISTATS 2018 Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings ICML 2018 Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap AISTATS 2018 Near-optimal Bayesian Active Learning with Correlated and Noisy Tests AISTATS 2017 Stochastic Submodular Maximization: The Case of Coverage Functions NIPS 2017 Gradient Methods for Submodular Maximization NIPS 2017 Fast and Provably Good Seedings for k-Means NIPS 2016 Sampling from Probabilistic Submodular Models NIPS 2015