collaborators

6 papers

cs.CV2026

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally

Darina Koishigarina, Arnas Uselis, Seong Joon Oh

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent composition…

cs.CV2025

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Yujin Jeong, Arnas Uselis, Seong Joon Oh +1

Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional un…

cs.LG2025

First Hallucination Tokens Are Different from Conditional Ones

Jakob Snel, Seong Joon Oh

Large Language Models (LLMs) hallucinate, and detecting these cases is key to ensuring trust. While many approaches address hallucination detection at the response or span level, r…

cs.LG2025

Does Data Scaling Lead to Visual Compositional Generalization?

Arnas Uselis, Andrea Dittadi, Seong Joon Oh

Compositional understanding is crucial for human intelligence, yet it remains unclear whether contemporary vision models exhibit it. The dominant machine learning paradigm is built…

cs.CV2025

On the rankability of visual embeddings

Ankit Sonthalia, Arnas Uselis, Seong Joon Oh

We study whether visual embedding models capture continuous, ordinal attributes along linear directions, which we term _rank axes_. We define a model as _rankable_ for an attribute…

cs.LG2025

Intermediate Layer Classifiers for OOD generalization

Arnas Uselis, Seong Joon Oh

Deep classifiers are known to be sensitive to data distribution shifts, primarily due to their reliance on spurious correlations in training data. It has been suggested that these…