| Fastseq: Make sequence generation faster Y Yan, F Hu, J Chen, N Bhendawade, T Ye, Y Gong, N Duan, D Cui, B Chi, ... arXiv preprint arXiv:2106.04718, 2021 | 16 | 2021 |
| Speculative Streaming: Fast LLM Inference without Auxiliary Models N Bhendawade, I Belousova, Q Fu, H Mason, M Rastegari, M Najibi arXiv preprint arXiv:2402.11131, 2024 | 12 | 2024 |
| El-attention: Memory efficient lossless attention for generation Y Yan, J Chen, W Qi, N Bhendawade, Y Gong, N Duan, R Zhang International Conference on Machine Learning, 11648-11658, 2021 | 5 | 2021 |
| Novel cochlear filter based cepstral coefficients for classification of unvoiced fricatives N Singh, N Bhendawade, HA Patil Int. J. Natural Lang. Comput 3 (4), 21-40, 2014 | 2 | 2014 |
| Resource-Efficient Attention in a Neural Network Y Yan, J Chen, N Bhendawade, G Yeyun, N Duan, R Zhang US Patent App. 17/221,791, 2022 | | 2022 |
| Spoken Keyword Retrieval Using Source and System Features MC Madhavi, HA Patil, N Bhendawade International Conference on Pattern Recognition and Machine Intelligence …, 2017 | | 2017 |
