activity
20242026
collaborators

6 papers

cs.LG2026

DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts

Guiquan Sun, Xikun Zhang, Jingchao Ni +1

Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typically adopt a task-based formula…

cs.LG2025

SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasters

ChengAo Shen, Ziming Zhao, Hanghang Tong +4

Time series AI is crucial for analyzing dynamic web content, driving a surge of pre-trained large models known for their strong knowledge encoding and transfer capabilities across…

cs.LG2025

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

ChengAo Shen, Wenchao Yu, Ziming Zhao +4

Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMV…

cs.LG2025

Harnessing Vision Models for Time Series Analysis: A Survey

Jingchao Ni, Ziming Zhao, ChengAo Shen +5

Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs).…

cs.LG2025

From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?

Ziming Zhao, ChengAo Shen, Hanghang Tong +4

Transformer-based models have gained increasing attention in time series research, driving interest in Large Language Models (LLMs) and foundation models for time series analysis.…

cs.LG2024

Rank Supervised Contrastive Learning for Time Series Classification

Qianying Ren, Dongsheng Luo, Dongjin Song

Recently, various contrastive learning techniques have been developed to categorize time series data and exhibit promising performance. A general paradigm is to utilize appropriate…