Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/9ICML 2026Poster· Deep Learning / Large Language Models

UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling

Kaiyu Huang · Xingyu Wang · Mingze Kong · Zhubo Shi · Yuqian Hou · Hong Xu · Zhongxiang Dai · Minchen Yu · Qingjiang Shi

推理效率与系统OpenReview

作者位次 #3/10ICML 2026Poster· Deep Learning / Large Language Models

T-POP: Test-Time Personalization with Online Preference Feedback

Zikun Qu · Min Zhang · Mingze Kong · Xiang Li · Zhiwei Shang · Zhiyong Wang · Yikun Ban · Shuang Qiu · Yao Shu · Zhongxiang Dai

对齐与偏好OpenReview

作者位次 #3/6ICML 2026Poster· Deep Learning / Large Language Models

ALSO: Adversarial Online Strategy Optimization for Social Agents

Xiang Li · Liping Yi · Mingze Kong · Min Zhang · Zhongxiang Dai · Qinghua Hu

智能体与工具安全社会与人本OpenReview

作者位次 #5/8ICML 2026Spotlight· Deep Learning / Large Language Models

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks

Zhi Hong · Qian Zhang · Jiahang Sun · Zhiwei Shang · Mingze Kong · Xiangyi Wang · Yao Shu · Zhongxiang Dai

智能体与工具OpenReview

作者位次 #3/7ACL 2026Findings· Findings of ACL

MTO : A Multi-turn Conversational Text-to- O verpass QL Dataset for Enhanced O pen S treet M ap Query Generation

Haodi Zhang · Xinrui Zhu · Mingze Kong · Zhidan Liu · Tao Fan · Kaishun Wu · Yuanfeng SONG

摘要

We propose a comprehensive framework for constructing multi-turn Text-to-OverpassQL dialogue datasets. Under this framework, we introduce the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus. Our dataset comprises over 7,800 dialogues, each containing 2 to 4 user utter...

评测与基准数据与预训练对齐与偏好OpenReview 项目页

Mingze Kong

获取完整研究档案

联系方式