2 papers
cs.CL2023
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Chenglong Wang, Hang Zhou, Yimin Hu +5
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requ…
cs.CV2023
ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Xiao Xu, Bei Li, Chenfei Wu +6
Two-Tower Vision-Language (VL) models have shown promising improvements on various downstream VL tasks. Although the most advanced work improves performance by building bridges bet…