Image de couverture de livre

Does Data Scaling Lead to Visual Compositional Generalization?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Uselis, Arnas, Dittadi, Andrea, Oh, Seong Joon
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
par: Uselis, Arnas, et autres
Publié: (2026)

Intermediate Layer Classifiers for OOD generalization
par: Uselis, Arnas, et autres
Publié: (2025)

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally
par: Koishigarina, Darina, et autres
Publié: (2025)

How can embedding models bind concepts?
par: Uselis, Arnas, et autres
Publié: (2026)

MEME: Multi-entity & Evolving Memory Evaluation
par: Jung, Seokwon, et autres
Publié: (2026)

On the rankability of visual embeddings
par: Sonthalia, Ankit, et autres
Publié: (2025)

Half-Truths Break Similarity-Based Retrieval
par: Kargi, Bora, et autres
Publié: (2026)

Diffusion Classifiers Understand Compositionality, but Conditions Apply
par: Jeong, Yujin, et autres
Publié: (2025)

Task-Synchronized Recurrent Neural Networks
par: Lukoševičius, Mantas, et autres
Publié: (2022)

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
par: Morelli, Fabian, et autres
Publié: (2026)

When Do Diffusion Models learn to Generate Multiple Objects?
par: Jeong, Yujin, et autres
Publié: (2026)

When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
par: Nielsen, Beatrix M. G., et autres
Publié: (2025)

First Hallucination Tokens Are Different from Conditional Ones
par: Snel, Jakob, et autres
Publié: (2025)

Pretrained Visual Uncertainties
par: Kirchhof, Michael, et autres
Publié: (2024)

Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
par: Mucsányi, Bálint, et autres
Publié: (2024)

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
par: Puerto, Haritz, et autres
Publié: (2024)

Are Object-Centric Representations Better At Compositional Generalization?
par: Kapl, Ferdinand, et autres
Publié: (2026)

Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction
par: Pauline, Vincent, et autres
Publié: (2025)

Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents
par: Kortukov, Evgenii, et autres
Publié: (2024)

Scalable Ensemble Diversification for OOD Generalization and Detection
par: Rubinstein, Alexander, et autres
Publié: (2024)

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
par: Chang, Hoyeon, et autres
Publié: (2026)

Calibrating Large Language Models Using Their Generations Only
par: Ulmer, Dennis, et autres
Publié: (2024)

Does Differentially Private Synthetic Data Lead to Synthetic Discoveries?
par: Perez, Ileana Montoya, et autres
Publié: (2024)

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
par: Rubinstein, Alexander, et autres
Publié: (2025)

Do Deep Neural Network Solutions Form a Star Domain?
par: Sonthalia, Ankit, et autres
Publié: (2024)

Scratching Visual Transformer's Back with Uniform Attention
par: Hyeon-Woo, Nam, et autres
Publié: (2022)

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
par: Joshi, Shruti, et autres
Publié: (2025)

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models
par: Mamaghan, Amir Mohammad Karimi, et autres
Publié: (2024)

A Good Score Does not Lead to A Good Generative Model
par: Li, Sixu, et autres
Publié: (2024)

Universal Algorithm-Implicit Learning
par: Woerner, Stefano, et autres
Publié: (2026)

Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts
par: Esfandiari, Yasin, et autres
Publié: (2025)

From Words to Amino Acids: Does the Curse of Depth Persist?
par: Siji, Aleena, et autres
Publié: (2026)

Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI
par: Nguyen, Elisa, et autres
Publié: (2024)

Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
par: Palma, Alessandro, et autres
Publié: (2024)

Flow-Based Density Ratio Estimation for Intractable Distributions with Applications in Genomics
par: Antipov, Egor, et autres
Publié: (2026)

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
par: Ju, Yeong-Joon, et autres
Publié: (2025)

DiffEnc: Variational Diffusion with a Learned Encoder
par: Nielsen, Beatrix M. G., et autres
Publié: (2023)

Are We Done with Object-Centric Learning?
par: Rubinstein, Alexander, et autres
Publié: (2025)

Logit Distance Bounds Representational Similarity
par: Nielsen, Beatrix M. G., et autres
Publié: (2026)

LLM generation novelty through the lens of semantic similarity
par: Davydov, Philipp, et autres
Publié: (2025)