2 papers
cs.LG2026
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
Zeyuan Wang, Da Li, Yulin Chen +6
Combining entropy regularisation with mirror descent in online off-policy reinforcement learning requires expressive policies with efficient sampling and explicit entropy control.…
cs.CV2025
Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis
Yihang Guo, Tianyuan Yu, Liang Bai +4
Multi-task learning (MTL) aims to build general-purpose vision systems by training a single network to perform multiple tasks jointly. While promising, its potential is often hinde…