papers

Publications (70)

cs.CV2025

Learning Robust Representations via Bidirectional Transition for Visual Reinforcement Learning

Xiaobo Hu, Youfang Lin, Yue Liu +4

Visual reinforcement learning has proven effective in solving control tasks with high-dimensional observations. However, extracting reliable and generalizable representations from…

cs.LG2026

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

Zhaoyang Ma, Zhihao Wu, Xin Gao +3

FedTopo introduces a method for federated learning with heterogeneous client models that shares class relation topologies instead of raw model parameters, enabling more reliable kn…

#federated learning#model heterogeneity#topology sharing#knowledge aggregation
eess.SY2024

DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data

Hanyang Chen, Yang Jiang, Shengnan Guo +3

The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC ass…

eess.SP2021

Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification

Ziyu Jia, Youfang Lin, Jing Wang +5

Sleep stage classification is essential for sleep assessment and disease diagnosis. Although previous attempts to classify sleep stages have achieved high classification performanc…

eess.SP2021

SleepPriorCL: Contrastive Representation Learning with Prior Knowledge-based Positive Mining and Adaptive Temperature for Sleep Staging

Hongjun Zhang, Jing Wang, Qinfeng Xiao +2

The objective of this paper is to learn semantic representations for sleep stage classification from raw physiological time series. Although supervised methods have gained remarkab…

cs.CV2023

View Adaptive Light Field Deblurring Networks with Depth Perception

Zeqi Shen, Shuo Zhang, Zhuhao Zhang +3

The Light Field (LF) deblurring task is a challenging problem as the blur images are caused by different reasons like the camera shake and the object motion. The single image deblu…