← Search

Sharad Mehrotra

2 accepted papers

2026

Unifying Stacking and Cascading for Efficient Ensemble Inference

ICML 2026poster

We introduce LazyStack, a method for efficient model ensemble inference. The core idea is intuitive: after each model executes, we check whether accumulated evidence is sufficient to exit confidently. Sometimes one model suffices; other times we aggregate predictions from several models via trained …

Cited by 0SourceScholar
2024

Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding

ACL 2024long

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The drafting stage generates draft tokens at a slightly lower quali…