4 citations · 9 across the 6 of their papers we have counts for
7 papers
MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
Jana Zeller, Thaddäus Wiedemer, Fanfei Li +6
Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interlea…
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick +2
Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and compute. More recently, loss-to-loss sca…
In Search of Forgotten Domain Generalization
Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer +4
Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets…
Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak +2
Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few…
Provable Compositional Generalization for Object-Centric Learning
Thaddäus Wiedemer, Jack Brady, Alexander Panfilov +3
Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learn…
Compositional Generalization from First Principles
Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge +1
Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achie…
Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks
Jörg Wagner, Jan Mathias Köhler, Tobias Gindele +3
To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a pos…