paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

NS

Naomi Saphra

ICML 2026×4理论与学习动力学可解释性社会与人本

新星分资深

26

一作贡献0

核心/参与14

方向广度6

合作网络12

0 一作 · 4 篇 · ICML 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

4

作者位次 #6/6ICML 2026Oral

Position: Don't Just "Fix it in Post'': A Science of AI Must Study Learning Dynamics

Stella Biderman · Mohammad Aflah Khan · Niloofar Mireshghallah · Catherine Arnett · Fazl Barez · Naomi Saphra

理论与学习动力学OpenReview

作者位次 #7/12ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability

Position: Interpretability Can Be Actionable

Hadas Orgad · Fazl Barez · Tal Haklay · Isabelle Lee · Marius Mosbach · Anja Reusch · Naomi Saphra · Byron Wallace · Sarah Wiegreffe · Eric Wong · Ian Tenney · Mor Geva

可解释性社会与人本OpenReview

作者位次 #4/5ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability

Do Activation Verbalization Methods Convey Privileged Information?

Millicent Li · Alberto Mario Ceballos Arroyo · Giordano Rogers · Naomi Saphra · Byron Wallace

可解释性社会与人本OpenReview

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

Random Scaling of Emergent Capabilities

Rosie Zhao · Tian Qin · David Alvarez-Melis · Sham Kakade · Naomi Saphra

理论与学习动力学OpenReview

常见合作者

FBFazl Barez×2 BWByron Wallace×2 SBStella Biderman MKMohammad Aflah Khan NMNiloofar Mireshghallah CACatherine Arnett HOHadas Orgad THTal Haklay ILIsabelle Lee MMMarius Mosbach ARAnja Reusch SWSarah Wiegreffe