Nish Sinnadurai — accepted AI-conference papers

2026

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

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

ICLR 2026poster

Sparsely-activated Mixture-of-Experts (SMoE) models offer efficient pre-training and low latency but their large parameter counts create significant memory overhead, motivating research into expert compression. Contrary to recent findings favouring expert *merging* on discriminative benchmarks, we f…

Cited by 0 Source ↗code ↗Scholar ↗

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

EMNLP 2025

Speculative decoding significantly accelerates language model inference by enabling a lightweight draft model to propose multiple tokens that a larger target model verifies simultaneously. However, applying this technique to vision-language models (VLMs) presents two fundamental challenges: small la

Cited by 0 Source ↗PDF ↗Scholar ↗