papers

Publications (14)

cs.CV2024

From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?

Chang'an Yi, Haotian Chen, Yifan Zhang +3

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classifica…

cs.LG2023

Model-Contrastive Federated Domain Adaptation

Chang'an Yi, Haotian Chen, Yonghui Xu +1

Federated domain adaptation (FDA) aims to collaboratively transfer knowledge from source clients (domains) to the related but different target client, without communicating the loc…

cs.LG2023

MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series

Qianwen Meng, Hangwei Qian, Yong Liu +3

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recentl…

q-bio.NC2021

Major Depressive Disorder Recognition and Cognitive Analysis Based on Multi-layer Brain Functional Connectivity Networks

Xiaofang Sun, Xiangwei Zheng, Yonghui Xu +2

On the increase of major depressive disorders (MDD), many researchers paid attention to their recognition and treatment. Existing MDD recognition algorithms always use a single tim…

cs.CL2025

LexPro-1.0 Technical Report

Haotian Chen, Yanyu Xu, Boyan Wang +5

In this report, we introduce our first-generation reasoning model, LexPro-1.0, a large language model designed for the highly specialized Chinese legal domain, offering comprehensi…

cs.LG2023

Dual Graph Multitask Framework for Imbalanced Delivery Time Estimation

Lei Zhang, Mingliang Wang, Xin Zhou +5

Delivery Time Estimation (DTE) is a crucial component of the e-commerce supply chain that predicts delivery time based on merchant information, sending address, receiving address,…