paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
MH

Michael Hahn

AwardICML 2026×5ACL 2026×2理论与学习动力学可解释性社会与人本代码推理
新星分资深
39
一作贡献0
核心/参与32
方向广度13
合作网络12
0 一作 · 7 篇 · ICML 2026 / ACL 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

7
作者位次 #4/4ICML 2026Poster· Deep Learning / Large Language Models

How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning

Entang Wang · Yiwei Wang · Aleksandra Bakalova · Michael Hahn

理论与学习动力学OpenReview
作者位次 #3/4ACL 2026OralOutstanding Paper· Natural Language Processing

Systematicity between Forms and Meanings across Languages Supports Efficient Communication

Doreen Osmelak · Yang Xu · Michael Hahn · Kate McCurdy

摘要

Languages vary widely in how meanings map to word forms. These mappings have been found to support efficient communication; however, this theory does not account for systematic relations within word forms. We examine how a restricted set of grammatical meanings (e.g. person, number) are expressed...

推理效率与系统评测与基准OpenReview 项目页
作者位次 #4/5ACL 2026Findings· Findings of ACL

System-Mediated Attention Imbalances Make Vision-Language Models Say Yes

Tsan Tsai Chan · Varsha Suresh · Anisha Saha · Michael Hahn · Vera Demberg

摘要

Vision-language model (VLM) hallucination is commonly linked to imbalanced allocation of attention across input modalities: system, image and text. However, existing mitigation strategies tend towards an image-centric interpretation of these imbalances, often prioritising increased image attentio...

多模态可解释性安全OpenReview 项目页

常见合作者