Matthias Bethge
~Matthias_Bethge1
19
论文总数
9.5
年均投稿
平均评分
接收情况17/19
会议分布
ICLR
8
NeurIPS
5
ICML
4
COLM
2
发表论文 (19 篇)
202511 篇
4
What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses
NeurIPS 2025Poster
4
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
NeurIPS 2025Poster
4
Identifying latent state transitions in non-linear dynamical systems
ICLR 2025Poster
3
WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
ICML 2025Poster
4
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models
ICML 2025Poster
4
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
ICML 2025Poster
4
Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
COLM 2025Poster
4
Democratizing Evaluation with Infinity-Benchmarks: Sample-Level Heterogeneous Testing Over Arbitrary Capabilities
ICLR 2025withdrawn
3
A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
COLM 2025Poster
4
In Search of Forgotten Domain Generalization
ICLR 2025Spotlight
4
Great Models Think Alike and this Undermines AI Oversight
ICML 2025Spotlight
20248 篇
4
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli
NeurIPS 2024Poster
5
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
NeurIPS 2024Poster
4
Does CLIP’s generalization performance mainly stem from high train-test similarity?
ICLR 2024Poster
3
Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
ICLR 2024Poster
3
Provable Compositional Generalization for Object-Centric Learning
ICLR 2024Oral
5
Playing repeated games with Large Language Models
ICLR 2024withdrawn
4
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
NeurIPS 2024Poster
4
Most discriminative stimuli for functional cell type clustering
ICLR 2024Poster