| Ulsam: Ultra-lightweight subspace attention module for compact convolutional neural networks R Saini*, NK Jha*, B Das, S Mittal, CKC Mohan Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020 | 117* | 2020 |
| DeepReDuce: ReLU Reduction for Fast Private Inference NK Jha, Z Ghodsi, S Garg, B Reagen 🏆 38th International Conference on Machine Learning (ICML, Spotlight), 2021 …, 2021 | 103 | 2021 |
| Circa: Stochastic ReLUs for Private Deep Learning Z Ghodsi, NK Jha, B Reagen, S Garg 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 34, 2021 | 41 | 2021 |
| Sisyphus: A cautionary tale of using low-degree polynomial activations in privacy-preserving deep learning K Garimella, NK Jha, B Reagen Privacy Preserving Machine Learning Workshop (PPML@ACM CCS), 2021, 2021 | 28 | 2021 |
| Characterizing and optimizing end-to-end systems for private inference K Garimella, Z Ghodsi, NK Jha, S Garg, B Reagen Proceedings of the 28th ACM International Conference on Architectural …, 2023 | 25 | 2023 |
| Modeling data reuse in deep neural networks by taking data-types into cognizance NK Jha, S Mittal IEEE Transactions on Computers 70 (9), 2020 | 21 | 2020 |
| The ramifications of making deep neural networks compact NK Jha, S Mittal, G Mattela 2019 32nd International Conference on VLSI Design and 2019 18th …, 2019 | 18 | 2019 |
| Deeppeep: Exploiting design ramifications to decipher the architecture of compact dnns NK Jha, S Mittal, B Kumar, G Mattela ACM Journal on Emerging Technologies in Computing Systems (JETC) 17 (1), 1-25, 2020 | 17* | 2020 |
| DRACO: Co-optimizing hardware utilization, and performance of DNNs on systolic accelerator NK Jha, S Ravishankar, S Mittal, A Kaushik, D Mandal, M Chandra 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 574-579, 2020 | 13 | 2020 |
| E2GC: Energy-efficient group convolution in deep neural networks NK Jha*, R Saini*, S Nag, SC Mittal 2020 33rd International Conference on VLSI Design and 2020 19th …, 2020 | 12 | 2020 |
| DeepReShape: Redesigning neural networks for efficient private inference NK Jha, B Reagen Transactions on Machine Learning Research (TMLR), 2024, 2024 | 9 | 2024 |
| On the demystification of knowledge distillation: A residual network perspective NK Jha*, R Saini*, SC Mittal arXiv preprint arXiv:2006.16589, 2020 | 5 | 2020 |
| Cryptonite: Revealing the pitfalls of end-to-end private inference at scale K Garimella, NK Jha, Z Ghodsi, S Garg, B Reagen arXiv preprint arXiv:2111.02583, 2021 | 4 | 2021 |
| Data-type aware arithmetic intensity for deep neural networks NK Jha, S Mittal, S Avancha 37th IEEE International Conference on Computer Design (ICCD'19), 1-2, 2019 | 4 | 2019 |
| Hardware-Aware Co-Optimization of Deep Convolutional Neural Networks NK Jha Indian Institute of Technology Hyderabad, 2020 | 2 | 2020 |
| Entropy-Guided Attention for Private LLMs NK Jha, B Reagen The 6th AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI), 2025, 2025 | | 2025 |
| TruncFormer: Private LLM Inference Using Only Truncations P Yubeaton, JC Mo, K Garimella, NK Jha, B Reagen, C Hegde, S Garg arXiv preprint arXiv:2412.01042, 2024 | | 2024 |
| AERO: Softmax-Only LLMs for Efficient Private Inference NK Jha, B Reagen arXiv preprint arXiv:2410.13060, 2024 | | 2024 |
| ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models NK Jha, B Reagen 2nd Workshop on Attributing Model Behavior at Scale (NeurIPS 2024), 2024 | | 2024 |
| ICCD 2019 Poster Session List M Li, H Lin, Q Jiang, H An, CT Do, CH Kim, SW Chung, K Oh, J Park, ... | | |
Brandon ReagenAssistant Professor, New York UniversityOverená e-mailová adresa na: nyu.edu