Nish Sinnadurai

According to our database, Nish Sinnadurai authored at least 6 papers between 2024 and 2025.

Collaborative distances:

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

2025

TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding.

Aditya Sridhar, Nish Sinnadurai, Sean Lie, Vithursan Thangarasa

CoRR, November, 2025

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression.

Mike Lasby, Ivan Lazarevich, Nish Sinnadurai, Sean Lie, Yani Ioannou, Vithursan Thangarasa

CoRR, October, 2025

SD²: Self-Distilled Sparse Drafters.

Mike Lasby, Nish Sinnadurai, Valavan Manohararajah, Sean Lie, Vithursan Thangarasa

CoRR, April, 2025

Self-Data Distillation for Recovering Quality in Pruned Large Language Models.

Vithursan Thangarasa, Ganesh Venkatesh, Mike Lasby, Nish Sinnadurai, Sean Lie

Proceedings of the Eighth Conference on Machine Learning and Systems, 2025

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models.

Mugilan Ganesan, Shane Segal, Ankur Aggarwal, Nish Sinnadurai, Sean Lie, Vithursan Thangarasa

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

Self-Data Distillation for Recovering Quality in Pruned Large Language Models.

Vithursan Thangarasa, Ganesh Venkatesh, Nish Sinnadurai, Sean Lie

CoRR, 2024