Image de couverture de livre

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Al-Tahan, Haider, Garrido, Quentin, Balestriero, Randall, Bouchacourt, Diane, Hazirbas, Caner, Ibrahim, Mark
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Bias of Harmful Label Associations in Vision-Language Models
par: Hazirbas, Caner, et autres
Publié: (2024)

Understanding the Detrimental Class-level Effects of Data Augmentation
par: Kirichenko, Polina, et autres
Publié: (2023)

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
par: Sobal, Vlad, et autres
Publié: (2024)

Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class
par: Moayeri, Mazda, et autres
Publié: (2024)

Beyond and Free from Diffusion: Invertible Guided Consistency Training
par: Hsu, Chia-Hong, et autres
Publié: (2025)

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
par: Van Assel, Hugues, et autres
Publié: (2025)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
par: Hsu, Chia-Hong, et autres
Publié: (2026)

BabyVision: Visual Reasoning Beyond Language
par: Chen, Liang, et autres
Publié: (2026)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
par: Balestriero, Randall, et autres
Publié: (2025)

Learning by Reconstruction Produces Uninformative Features For Perception
par: Balestriero, Randall, et autres
Publié: (2024)

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
par: Eastwood, Cian, et autres
Publié: (2023)

VISReg: Variance-Invariance-Sketching Regularization for JEPA training
par: Wu, Haiyu, et autres
Publié: (2026)

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
par: Humayun, Ahmed Imtiaz, et autres
Publié: (2023)

Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
par: Przewięźlikowski, Marcin, et autres
Publié: (2024)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
par: Ibrahim, Mark, et autres
Publié: (2024)

Interpreting Physics in Video World Models
par: Joseph, Sonia, et autres
Publié: (2026)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
par: Otero, Daniel, et autres
Publié: (2024)

CompareBench: A Benchmark for Visual Comparison Reasoning in Vision-Language Models
par: Cai, Jie, et autres
Publié: (2025)

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
par: Zhou, Yucheng, et autres
Publié: (2024)

VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models
par: Ren, Yufan, et autres
Publié: (2025)

End-to-end Topographic Auditory Models Replicate Signatures of Human Auditory Cortex
par: Al-Tahan, Haider, et autres
Publié: (2025)

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations
par: Bisulco, Anthony, et autres
Publié: (2025)

Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
par: Xia, Xue, et autres
Publié: (2024)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
par: Jiang, Houcheng, et autres
Publié: (2026)

Deep Networks Always Grok and Here is Why
par: Humayun, Ahmed Imtiaz, et autres
Publié: (2024)

On the Geometry of Deep Learning
par: Balestriero, Randall, et autres
Publié: (2024)

LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
par: Liu, Lu, et autres
Publié: (2026)

Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
par: Xiong, Guangzhi, et autres
Publié: (2026)

UniREditBench: A Unified Reasoning-based Image Editing Benchmark
par: Han, Feng, et autres
Publié: (2025)

GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models
par: Xie, Qinghongbing, et autres
Publié: (2025)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
par: Feizi, Aarash, et autres
Publié: (2024)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
par: Balestriero, Randall, et autres
Publié: (2025)

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
par: Lu, Wenquan, et autres
Publié: (2025)

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
par: Luo, Zhiming, et autres
Publié: (2026)

A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
par: Terver, Basile, et autres
Publié: (2026)

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
par: Liu, Jie, et autres
Publié: (2026)

The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
par: Kitouni, Ouail, et autres
Publié: (2024)

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
par: Zhang, Jiaqi, et autres
Publié: (2025)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
par: Zhang, Ce, et autres
Publié: (2025)

ViUniT: Visual Unit Tests for More Robust Visual Programming
par: Panagopoulou, Artemis, et autres
Publié: (2024)