activity
20232026
most citedEFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

CoDrift: Compositional Drifting for Offline Reinforcement Learning

Xiewei Ni, Ruofeng Mei, Xiangyu Xu

Offline reinforcement learning is intrinsically multi-objective: a policy must remain compatible with the behavioral support of a fixed dataset while preferentially selecting high-…

cs.LG2026

TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation

Xiangyu Xu, Qingsong Zhong, Jilin Hu

Generative modeling offers a promising solution to data scarcity and privacy challenges in time series analysis. However, the structural complexity of time series, characterized by…