影响力指数

87.59/100

前 0.8%

全站排名 #484

发表论文19 篇

平均评分6.1

年均产出6.3 篇/年

Wieland Brendel

Principal Researcher@ELLIS Institute Tübingen·德国·OpenReview

研究方向

deep learning · adversarial robustness · generative models · representation learning · unsupervised learning

7.0

Low-Pass Filtering Improves Behavioral Alignment of Vision Models

ICLR 2026Poster

通讯

6.0

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

ICLR 2026Poster

通讯

5.5

Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers

NeurIPS 2025Poster

三作

6.5

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

ICLR 2025Spotlight

通讯

5.5

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models

ICML 2025Poster

三作

5.5

LAION-C: An out-of-distribution benchmark for web-scale vision models

ICLR 2025Rejected

三作

4.4

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws

合作者 (20)

Prasanna Mayilvahanan

4 篇

Patrik Reizinger

4 篇

Wieland Brendel

Low-Pass Filtering Improves Behavioral Alignment of Vision Models

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

Generation is Required for Data-Efficient Perception

OVid: Open Large-Scale Video Dataset as a Novel Source for Image-Text Data

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model

Cross-Entropy Is All You Need To Invert the Data Generating Process

In Search of Forgotten Domain Generalization

Interaction Asymmetry: A General Principle for Learning Composable Abstractions

Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models

LAION-C: An out-of-distribution benchmark for web-scale vision models

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws