Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/10ICLR 2026Poster· Applications / Time Series

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

Tong Guan · Zijie Meng · Dianqi Li · Shiyu Wang · Chao-Han Huck Yang · Qingsong Wen · Zuozhu Liu · Sabato Siniscalchi · Ming Jin · Shirui Pan

推理OpenReview

作者位次 #2/5ACL 2026Poster· Natural Language Processing

STR easoner: Empowering LLM s for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

Juntong Ni · Shiyu Wang · Qi He · Ming Jin · Wei Jin

摘要

Spatio-temporal reasoning in time series involves the explicit synthesis of temporal dynamics, spatial dependencies, and textual context. This capability is vital for high-stakes decision-making in systems such as traffic networks, power grids, and disease propagation. However, the field remains...

推理智能体与工具强化学习与后训练OpenReview 项目页

作者位次 #3/5KDD 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

Shiyu Wang

获取完整研究档案

联系方式

2026 顶会论文

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

STR easoner: Empowering LLM s for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

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

常见合作者