#artificial intelligence
Jan 2026
HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning
This work proposes Homura, a reinforcement learning framework that explicitly optimizes the trade-off between semantic preservation and temporal compliance, and demonstrates that Homura significantly outperforms strong baselines, achieving precise length control that respects linguistic density hierarchies without comp...
Ziang Cui, Mengran Yu, Tian-Jiao Li et al.
· arXiv.org · 0 citations