Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/5ICML 2026Poster· Reinforcement Learning / Everything Else

Mitigating Plasticity Loss through Architectural Design in Continual Learning

Niklas Koeppe · Luiz Felipe Vecchietti · Dongqi Han · Dongsheng Li · Sang Wan Lee

强化学习与后训练OpenReview

作者位次 #4/8ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

Marcelo Sartori Locatelli · Fernando Tonucci · Jea Kwon · Luiz Felipe Vecchietti · Bryan Nathanael Wijaya · Cheng Yaw Low · Virgilio Almeida · MEEYOUNG CHA

可解释性多模态社会与人本OpenReview

作者位次 #3/6ACL 2026Findings· Findings of ACL

Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions

Jiseon Kim · Jea Kwon · Luiz Felipe Vecchietti · Wenchao Dong · Jaehong Kim · Meeyoung Cha

摘要

Human moral judgment is context-dependent and changes based on interpersonal relationships. As large language models (LLMs) increasingly serve as decision-support systems, it is critical to understand if they encode these social nuances. We characterize LLM behavior using the Whistleblower’s Dile...

社会与人本推理评测与基准OpenReview 项目页

作者位次 #2/4AAAI 2026Poster· Artificial Intelligence

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment

Jea Kwon · Luiz Felipe Vecchietti · Sungwon Park · Meeyoung Cha

社会与人本对齐与偏好OpenReview

Luiz Felipe Vecchietti

获取完整研究档案

联系方式

2026 顶会论文

Mitigating Plasticity Loss through Architectural Design in Continual Learning

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment

常见合作者