Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/4ICLR 2026Poster· Optimization / Learning for Optimization

Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs

Shuangchun Gui · Suyu Liu · Xuehe Wang · Zhiguang Cao

作者位次 #6/12ICLR 2026Poster· Applications / Climate

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models

Shilei Cao · Hehai Lin · Jiashun Cheng · Yang Liu · Guowen Li · Xuehe Wang · Juepeng Zheng · Haoyuan Liang · Meng Jin · Chengwei Qin · Hong Cheng · Haohuan Fu

强化学习与后训练效率与系统OpenReview

作者位次 #6/14ICLR 2026Poster· Applications / Climate

TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology State

Guowen Li · Xintong Liu · Yang Liu · Mengxuan Chen · Shilei Cao · Xuehe Wang · Juepeng Zheng · Jinxiao Zhang · Haoyuan Liang · Lixian Zhang · Jiuke Wang · Meng Jin · Hong Cheng · Haohuan Fu

OpenReview

作者位次 #4/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Domain Sensitive Federated Learning with Fisher-Informed Pruning

Chenchen Lin · Wenhao Yuan · Zhengji Xu · Xuehe Wang

多模态效率与系统OpenReview 项目页

作者位次 #5/6ACL 2026Poster· Natural Language Processing

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing

Wenhao Yuan · Chenchen Lin · Jian Chen · Jinfeng Xu · Xuehe Wang · Edith Cheuk-Han Ngai

摘要

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing unsupported beliefs repeatedly stored and propagated across deci...

推理智能体与工具安全OpenReview 项目页

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

LEAP: Learning-Dynamics-Guided Open-Loop Pricing for LLM Data Acquisition

Zhiheng Wang · Xuehe Wang

检索与知识OpenReview

Xuehe Wang

获取完整研究档案

联系方式