Program synthesis using natural language A Desai, S Gulwani, V Hingorani, N Jain, A Karkare, M Marron, S Roy Proceedings of the 38th International Conference on Software Engineering …, 2016 | 160 | 2016 |
Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time Z Liu, A Desai, F Liao, W Wang, V Xie, Z Xu, A Kyrillidis, A Shrivastava Advances in Neural Information Processing Systems 36, 2024 | 26 | 2024 |
Random Offset Block Embedding (ROBE) for compressed embedding tables in deep learning recommendation systems A Desai, L Chou, A Shrivastava Proceedings of Machine Learning and Systems 4, 762-778, 2022 | 22* | 2022 |
Semantically constrained memory allocation (scma) for embedding in efficient recommendation systems A Desai, Y Pan, K Sun, L Chou, A Shrivastava arXiv preprint arXiv:2103.06124, 2021 | 10 | 2021 |
Raw nav-merge seismic data to subsurface properties with mlp based multi-modal information unscrambler A Desai, Z Xu, M Gupta, A Chandran, A Vial-Aussavy, A Shrivastava Advances in Neural Information Processing Systems 34, 8740-8752, 2021 | 8 | 2021 |
Active sampling count sketch (ascs) for online sparse estimation of a trillion scale covariance matrix Z Dai, A Desai, R Heckel, A Shrivastava Proceedings of the 2021 International Conference on Management of Data, 352-364, 2021 | 6 | 2021 |
The trade-offs of model size in large recommendation models: 100GB to 10MB Criteo-tb DLRM model A Desai, A Shrivastava Advances in Neural Information Processing Systems 35, 33961-33972, 2022 | 5 | 2022 |
Hardware-aware compression with random operation access specific tile (ROAST) hashing A Desai, K Zhou, A Shrivastava International Conference on Machine Learning, 7732-7749, 2023 | 2* | 2023 |
Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces A Desai, B Meisburger, Z Liu, A Shrivastava arXiv preprint arXiv:2311.01722, 2023 | 1 | 2023 |
HashOrder: Accelerating Graph Processing Through Hashing-based Reordering T Zhang, A Desai, G Gupta, A Shrivastava | 1 | 2023 |
The trade-offs of model size in large recommendation models: A 10000x compressed criteo-TB DLRM model (100 GB parameters to mere 10MB) A Desai, A Shrivastava Advances in Neural Information Processing Systems 2022 (NeurIPS 2022), 2022 | 1 | 2022 |
Beyond convolutions: A novel deep learning approach for raw seismic data ingestion Z Xu, A Desai, M Gupta, A Chandran, A Vial-Aussavy, A Shrivastava arXiv preprint arXiv:2102.13631, 2021 | 1 | 2021 |
Density Sketches for Sampling and Estimation A Desai, B Coleman, A Shrivastava arXiv preprint arXiv:2102.12301, 2021 | 1 | 2021 |
Facilitating Verification in Program Loops by Identification of Static Iteration Patterns A Desai, E Jain, S Roy 2013 20th Asia-Pacific Software Engineering Conference (APSEC) 1, 83-90, 2013 | 1 | 2013 |
In defense of parameter sharing for model-compression A Desai, A Shrivastava arXiv preprint arXiv:2310.11611, 2023 | | 2023 |
Embedding models through the lens of Stable Coloring A Desai, S Sonkar, A Shrivastava, R Baraniuk | | 2021 |