Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/7ICML 2026Poster· General Machine Learning / Clustering

Incomplete Multi-View Clustering via Neighborhood-Conditioned Diffusion

Qian Guo · Gaohui Zuo · Bingbing Jiang · Guangrui Fan · Zhihua Cui · Xinyan Liang · Jianjian Ding

OpenReview

一作ICML 2026Poster· Deep Learning / Algorithms

Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare Estimation

Guangrui Fan · DanDan Liu · AZNUL SABRI · Pan Lihu

社会与人本对齐与偏好OpenReview

一作ACL 2026Poster· Natural Language Processing

Feeling Rules in Language Models: Mapping Norms of Emotional Appropriateness Across Roles, Institutions, and Intensity

Guangrui Fan · DanDan Liu · Aznul Qalid MD Sabri · Rui Zhang · Pan Lihu

摘要

When asked explicitly, a Large language model (LLM) may validate your anger—but implicitly, it may still judge that anger as inappropriate. We call this divergence the endorsement–exposure gap, and it reveals that LLMs encode hidden norms about which emotions are acceptable in which contexts. To...

评测与基准对齐与偏好可解释性OpenReview 项目页

一作CHI 2026Oral· Human-Computer Interaction

When Help Hurts: Verification Load and Fatigue with AI Coding Assistants

Guangrui Fan · DanDan Liu · Pan Lihu · Rui Zhang

代码社会与人本OpenReview

一作CHI 2026Oral· Human-Computer Interaction

Is It Still You? Attributing Authorship and Authenticity in AI-Assisted Romantic Communication

Guangrui Fan · DanDan Liu · Pan Lihu

社会与人本OpenReview

一作CHI 2026Oral· Human-Computer Interaction

Co‑Adaptive Eco‑Nudging: A Privacy‑Preserving Contextual Bandit with User‑Taught Preferences in Everyday Browsing

Guangrui Fan · DanDan Liu · Pan Lihu

对齐与偏好安全社会与人本OpenReview

一作AAAI 2026Poster· Artificial Intelligence

Mind the Gap: Predicting, Explaining and Reducing Time-to-First-Comment (Reply Gap) in Online Mental-Health Communities

Guangrui Fan · DanDan Liu · Pan Lihu

社会与人本OpenReview

Guangrui Fan

获取完整研究档案

联系方式

2026 顶会论文

Incomplete Multi-View Clustering via Neighborhood-Conditioned Diffusion

Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare Estimation

Feeling Rules in Language Models: Mapping Norms of Emotional Appropriateness Across Roles, Institutions, and Intensity

When Help Hurts: Verification Load and Fatigue with AI Coding Assistants

Is It Still You? Attributing Authorship and Authenticity in AI-Assisted Romantic Communication

Co‑Adaptive Eco‑Nudging: A Privacy‑Preserving Contextual Bandit with User‑Taught Preferences in Everyday Browsing

Mind the Gap: Predicting, Explaining and Reducing Time-to-First-Comment (Reply Gap) in Online Mental-Health Communities

常见合作者