Author

Tanmoy Chakraborty

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

It Takes a MAESTRO To Prune Bad Experts

MAESTRO (Markov-chain Approximated Expert Sparsification via Transition-based ROuting), a structured pruning framework designed for MoE architectures that models autoregressive expert activation trajectories as Ergodic Markov chains whose stationary distributions encode cross-layer dependencies, yielding a globally aware importance heuristic is introduced.

Palaash Goel, Ayush Maheshwari, Tanmoy Chakraborty · 1 citation