Nikhil Bhendawade

Orcid: 0000-0002-4574-3102

According to our database1, Nikhil Bhendawade authored at least 10 papers between 2017 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
The Design Space of Tri-Modal Masked Diffusion Models.
CoRR, February, 2026

2025
Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference.
CoRR, October, 2025

FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models.
CoRR, September, 2025

M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference.
CoRR, February, 2025

Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
Speculative Streaming: Fast LLM Inference without Auxiliary Models.
Proceedings of the NeurIPS Efficient Natural Language and Speech Processing Workshop, 2024

2021
FastSeq: Make Sequence Generation Faster.
CoRR, 2021

EL-Attention: Memory Efficient Lossless Attention for Generation.
Proceedings of the 38th International Conference on Machine Learning, 2021

FastSeq: Make Sequence Generation Faster.
Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

2017
Spoken Keyword Retrieval Using Source and System Features.
Proceedings of the Pattern Recognition and Machine Intelligence, 2017


  Loading...