most citedFrom Words to Amino Acids: Does the Curse of Depth Persist?

1 citations · 1 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV2026

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Arnas Uselis, Andrea Dittadi, Seong Joon Oh

Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern models are trained on massiv…

cs.LG2026

Scalable and Interpretable Representation Alignment with Ordinal Similarity

Diogo Soares, Pankhil Gawade, Andrea Dittadi +1

Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they lack interpretability due to shi…

cs.LG2026

Flow-Based Density Ratio Estimation for Intractable Distributions with Applications in Genomics

Egor Antipov, Alessandro Palma, Lorenzo Consoli +3

Estimating density ratios between pairs of intractable data distributions is a core problem in probabilistic modeling, enabling principled comparisons of sample likelihoods under d…

cs.LG20261 cited

From Words to Amino Acids: Does the Curse of Depth Persist?

Aleena Siji, Amir Mohammad Karimi Mamaghan, Ferdinand Kapl +9

Protein language models (PLMs) have become widely adopted as general-purpose models, demonstrating strong performance in protein engineering and de novo design. Like large language…

cs.CV2026

Are Object-Centric Representations Better At Compositional Generalization?

Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Maximilian Seitzer +4

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning.…

stat.ML2025

Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction

Vincent Pauline, Tobias Höppe, Tobias Höppe +4

Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom clarify their connection to discrete-…