works on
efficiency analysis 1kv cache sparsification 1large language models 1long-context inference 1speculative decoding 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding

Yuesong Liu, Yuan Zeng, Min Lyu +3

The paper proposes SparseSpec-L, a training-free self-speculative decoding method that uses a sparsified key‑value cache and an entropy‑based controller to speed up long‑context in…