Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

NeurIPSSpotlight2025

Authors
Xinyu Yang, Yuwei An, Hongyi Liu, Tianqi Chen, Beidi Chen
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Autoregressive Large Language Models (AR-LLMs) frequently exhibit implicit parallelism in sequential generation…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

large language model language model llm

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive