paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

MK

Marius Kloft

ICML 2026×6AAAI 2026×2强化学习与后训练理论与学习动力学安全多模态评测与基准

新星分资深

32

一作贡献0

核心/参与25

方向广度13

合作网络3

0 一作 · 8 篇 · ICML 2026 / AAAI 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

8

作者位次 #4/4ICML 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 #5/6ICML 2026Poster· Applications / Chemistry, Physics, and Earth Sciences

Physics-Informed Residual Flows

Jephte Abijuru · Mayank Kumar Nagda · Phil Sidney Ostheimer · Sebastian Vollmer · Marius Kloft · Sophie Fellenz

作者位次 #8/9ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Skipping the Zeros in Diffusion Models for Sparse Data Generation

Phil Sidney Ostheimer · Mayank Kumar Nagda · Andriy Balinskyy · Gabriel Rodrigues · Jean Radig · Carl Herrmann · Stephan Mandt · Marius Kloft · Sophie Fellenz

作者位次 #7/8ICML 2026Poster· Applications / Chemistry, Physics, and Earth Sciences

Heavy-tailed Physics-Informed Neural Networks

Jephte Abijuru · Mayank Kumar Nagda · Jan Tauberschmidt · Phil Sidney Ostheimer · Sebastian Vollmer · Stephan Mandt · Marius Kloft · Sophie Fellenz

作者位次 #7/7ICML 2026Poster· Applications / Computer Vision

Formally Exploring Visual Anomaly Detection Evaluation Metrics

Nasar Iqbal · Dennis Wagner · Philipp Liznerski · Nabeel Hussain Syed · Sophie Fellenz · Niki Martinel · Marius Kloft

多模态评测与基准OpenReview

作者位次 #4/5ICML 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 #8/8AAAI 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 #5/6AAAI 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

SFSophie Fellenz×5 PWPuyu Wang×4 PLPhilipp Liznerski×3 MNMayank Kumar Nagda×3 POPhil Sidney Ostheimer×3 JAJephte Abijuru×2 SVSebastian Vollmer×2 SMStephan Mandt×2 MMMarcio Monteiro×2 WLWeichen Li×2 SFSophie Fellenz×2 JZJunyu Zhou