works on
behavioral specification 1benchmark evaluation 1benchmarking 1binary exploration 1code generation 1coding agents 1LLM agents 1model fine-tuning 1non-functional improvements 1program synthesis 1python 1requirements engineering 1

From the 3 of 17 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States

Ximing Dong, Shaowei Wang, Dayi Lin +2

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large R…