Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/4ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability

Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering

Tiejin Chen · Longchao Da · Xiaoou Liu · Hua Wei

可解释性社会与人本OpenReview

一作ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

Xiaoou Liu · Tiejin Chen · Dengjia Zhang · Yaqing Wang · Lu Cheng · Hua Wei

推理可解释性社会与人本OpenReview

作者位次 #2/6ACL 2026Findings· Findings of ACL

Uncertainty Quantification of Large Language Models through Multiple Uncertainty Sources

Tiejin Chen · Xiaoou Liu · Longchao Da · Jia Chen · Evangelos E. Papalexakis · Hua Wei

摘要

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains. However, the reliability of responses from LLMs remains a question. Uncertainty quantification (UQ) of LLMs is crucial for ensuring their reliability, especially in areas such as healthcare. Existing UQ...

效率与系统评测与基准代码OpenReview 项目页

一作KDD 2026Oral· Knowledge Discovery & Data Mining

The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective

Xiaoou Liu · Tiejin Chen · Weibo Li · Xiyang Hu · Hua Wei

智能体与工具检索与知识OpenReview

作者位次 #2/5IROS 2026Oral· Perceiving and Reconstructing Plants in the Field

PlantShade: Predicting Plant Shadows for Lighting-Aware Robotic Agricultural Operation

Longchao Da · Xiaoou Liu · Xingjian Li · Lirong Xiang · Hua Wei

社会与人本Agricultural AutomationMachine Learning for Robot ControlSimulation and AnimationOpenReview

Xiaoou Liu

获取完整研究档案

联系方式