Length Optimization in Conformal Prediction S Kiyani, G Pappas, H Hassani arXiv preprint arXiv:2406.18814, 2024 | | 2024 |
Evaluating the Performance of Large Language Models via Debates B Moniri, H Hassani, E Dobriban arXiv preprint arXiv:2406.11044, 2024 | | 2024 |
Watermarking Language Models with Error Correcting Codes P Chao, E Dobriban, H Hassani arXiv preprint arXiv:2406.10281, 2024 | | 2024 |
Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks M Sabbaghi, G Pappas, H Hassani, S Goel arXiv preprint arXiv:2406.01895, 2024 | | 2024 |
One-Shot Safety Alignment for Large Language Models via Optimal Dualization X Huang, S Li, E Dobriban, O Bastani, H Hassani, D Ding arXiv preprint arXiv:2405.19544, 2024 | | 2024 |
Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models B Moniri, H Hassani arXiv preprint arXiv:2405.18274, 2024 | | 2024 |
Efficient and robust classification for sparse attacks M Beliaev, P Delgosha, H Hassani, R Pedarsani IEEE Journal on Selected Areas in Information Theory, 2024 | 2 | 2024 |
Conformal Prediction with Learned Features S Kiyani, G Pappas, H Hassani arXiv preprint arXiv:2404.17487, 2024 | 2 | 2024 |
Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling A Adibi, N Dal Fabbro, L Schenato, S Kulkarni, HV Poor, GJ Pappas, ... International Conference on Artificial Intelligence and Statistics, 2746-2754, 2024 | 3 | 2024 |
Model-based robust deep learning GJ Pappas, H Hassani, A Robey US Patent 11,961,283, 2024 | 3 | 2024 |
Uncertainty in language models: Assessment through rank-calibration X Huang, S Li, M Yu, M Sesia, H Hassani, I Lee, O Bastani, E Dobriban arXiv preprint arXiv:2404.03163, 2024 | 6 | 2024 |
The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression H Hassani, A Javanmard The Annals of Statistics 52 (2), 441-465, 2024 | 37 | 2024 |
Jailbreakbench: An open robustness benchmark for jailbreaking large language models P Chao, E Debenedetti, A Robey, M Andriushchenko, F Croce, V Sehwag, ... arXiv preprint arXiv:2404.01318, 2024 | 21 | 2024 |
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation Y He, A Robey, N Murata, Y Jiang, J Williams, GJ Pappas, H Hassani, ... arXiv preprint arXiv:2403.19103, 2024 | | 2024 |
Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding E Lei, H Hassani, SS Bidokhti arXiv preprint arXiv:2403.07320, 2024 | | 2024 |
Neural Compression with Lattice Transform Coding E Lei, H Hassani, S Saeedi Bidokhti International Zurich Seminar on Information and Communication (IZS 2024 …, 2024 | | 2024 |
Defending large language models against jailbreak attacks via semantic smoothing J Ji, B Hou, A Robey, GJ Pappas, H Hassani, Y Zhang, E Wong, S Chang arXiv preprint arXiv:2402.16192, 2024 | 14 | 2024 |
Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth K Kögler, A Shevchenko, H Hassani, M Mondelli arXiv preprint arXiv:2402.05013, 2024 | | 2024 |
Binary Classification Under ℓ0 Attacks for General Noise Distribution P Delgosha, H Hassani, R Pedarsani IEEE Transactions on Information Theory, 2023 | 1 | 2023 |
Score-Based Methods for Discrete Optimization in Deep Learning E Lei, A Adibi, H Hassani arXiv preprint arXiv:2310.09890, 2023 | | 2023 |