paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

PW

Puyu Wang

AAAI 2026×3ICML 2026×2理论与学习动力学强化学习与后训练安全对齐与偏好

新星分新星

75

一作贡献30

核心/参与27

方向广度11

合作网络9

1 一作 · 5 篇 · AAAI 2026 / 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

5

一作ICML 2026Poster· Deep Learning / Theory

Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks

Puyu Wang · Junyu Zhou · Philipp Liznerski · Marius Kloft

理论与学习动力学安全OpenReview

作者位次 #3/5ICML 2026Poster· Applications / Everything Else

Landmark-Guided Policy Optimization for Multi-Objective Language Model Selection

Marcio Monteiro · Weichen Li · Puyu Wang · Marius Kloft · Sophie Fellenz

强化学习与后训练OpenReview

作者位次 #4/8AAAI 2026Poster· Artificial Intelligence

Reimagining Anomalies: What If Anomalies Were Normal?

Philipp Liznerski · Saurabh Varshneya · Ece Calikus · Puyu Wang · Alexander Bartscher · Sebastian Josef Vollmer · Sophie Fellenz · Marius Kloft

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

Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs

Zhongjie Shi · Puyu Wang · Chenyang Zhang · Yuan Cao

理论与学习动力学OpenReview

作者位次 #4/6AAAI 2026Poster· Artificial Intelligence

TORA: Train Once, Realign Anytime for Offline Multi-Objective Reinforcement Learning

Weichen Li · Waleed Mustafa · Marcio Monteiro · Puyu Wang · Marius Kloft · Sophie Fellenz

对齐与偏好强化学习与后训练OpenReview

常见合作者

MKMarius Kloft×4 PLPhilipp Liznerski×2 MMMarcio Monteiro×2 WLWeichen Li×2 SFSophie Fellenz×2 JZJunyu Zhou SFSophie Fellenz SVSaurabh Varshneya ECEce Calikus ABAlexander Bartscher SVSebastian Josef Vollmer ZSZhongjie Shi