Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/7ICML 2026Poster· Deep Learning / Sequential Models, Time series

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks

Bohan Wang · Zewen Liu · Lu Lin · Hui Liu · Li Xiong · Ming Jin · Wei Jin

安全OpenReview

一作ACL 2026Findings· Findings of ACL

Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?

Zewen Liu · Juntong Ni · Xianfeng Tang · Max S. Y. Lau · Qi He · Wenpeng Yin · Wei Jin

摘要

Uncovering hidden symbolic laws from time series data, as an aspiration dating back to Kepler’s discovery of planetary motion, remains a core challenge in scientific discovery and artificial intelligence. While Large Language Models show promise in structured reasoning tasks, their ability to inf...

评测与基准推理对齐与偏好OpenReview 项目页

作者位次 #2/5KDD 2026Oral· Knowledge Discovery & Data Mining

TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation

Juntong Ni · Zewen Liu · Shiyu Wang · Ming Jin · Wei Jin

强化学习与后训练效率与系统检索与知识OpenReview

一作KDD 2026Oral· Knowledge Discovery & Data Mining

Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes

Zewen Liu · Juntong Ni · Bohan Wang · Max S. Y. Lau · Wei Jin

数据与预训练检索与知识OpenReview

Zewen Liu

获取完整研究档案

联系方式

2026 顶会论文

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks

Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?

TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation

Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes

常见合作者