Kumari Nishu

According to our database, Kumari Nishu authored at least 9 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference.

Nikhil Bhendawade, Kumari Nishu, Arnav Kundu, Chris Bartels, Minsik Cho, Irina Belousova

CoRR, October, 2025

MoE-PHDS: One MoE checkpoint for flexible runtime sparsity.

Lauren. A Hannah, Soheil Zibakhsh, Kumari Nishu, Arnav Kundu, Mohammad Samragh Razlighi, Mehrdad Farajtabar, Minsik Cho

CoRR, September, 2025

MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE.

Soheil Zibakhsh, Mohammad Samragh, Kumari Nishu, Lauren Hannah, Arnav Kundu, Minsik Cho

CoRR, September, 2025

Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential.

Mohammad Samragh, Arnav Kundu, David Harrison, Kumari Nishu, Devang Naik, Minsik Cho, Mehrdad Farajtabar

CoRR, July, 2025

From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs.

Kumari Nishu, Sachin Mehta, Samira Abnar, Mehrdad Farajtabar, Maxwell Horton, Mahyar Najibi, Moin Nabi, Minsik Cho, Devang Naik

CoRR, February, 2025

SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting.

Kumari Nishu, Minsik Cho, Devang Naik

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

Flexible Keyword Spotting Based on Homogeneous Audio-Text Embedding.

Kumari Nishu, Minsik Cho, Paul Dixon, Devang Naik

Proceedings of the IEEE International Conference on Acoustics, 2024

Improving Vision-Inspired Keyword Spotting Using Dynamic Module Skipping in Streaming Conformer Encoder.

Alexandre Bittar, Paul Dixon, Mohammad Samragh, Kumari Nishu, Devang Naik

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Matching Latent Encoding for Audio-Text based Keyword Spotting.

Kumari Nishu, Minsik Cho, Devang Naik

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023