Cover Image

Is the Modality Gap a Bug or a Feature? A Robustness Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chowers, Rhea, Naparstek, Oshri, Barzelay, Udi, Weiss, Yair
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective
by: Chowers, Rhea, et al.
Published: (2022)

Control+Shift: Generating Controllable Distribution Shifts
by: Friedman, Roy, et al.
Published: (2024)

REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
by: Wasserman, Navve, et al.
Published: (2025)

Complexity as Advantage: A Regret-Based Perspective on Emergent Structure
by: Naparstek, Oshri
Published: (2025)

Intriguing Properties of Modern GANs
by: Friedman, Roy, et al.
Published: (2024)

Projected Autoregression: Autoregressive Language Generation in Continuous State Space
by: Naparstek, Oshri
Published: (2026)

Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet
by: Niu, Xin, et al.
Published: (2026)

VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents
by: Barzelay, Udi, et al.
Published: (2026)

AFD: Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
by: Zhou, Nuoyan, et al.
Published: (2024)

Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning
by: Huang, Linlan, et al.
Published: (2025)

Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning
by: Role, François, et al.
Published: (2025)

Closing the Modality Gap Aligns Group-Wise Semantics
by: Grassucci, Eleonora, et al.
Published: (2026)

It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
by: Fahim, Abrar, et al.
Published: (2024)

Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap
by: Liao, Christopher, et al.
Published: (2024)

Bridge the Modality and Capability Gaps in Vision-Language Model Selection
by: Yi, Chao, et al.
Published: (2024)

Provable Uncertainty Decomposition via Higher-Order Calibration
by: Ahdritz, Gustaf, et al.
Published: (2024)

MMP: Towards Robust Multi-Modal Learning with Masked Modality Projection
by: Nezakati, Niki, et al.
Published: (2024)

Robult: Leveraging Redundancy and Modality Specific Features for Robust Multimodal Learning
by: Nguyen, Duy A., et al.
Published: (2025)

Narrowing Class-Wise Robustness Gaps in Adversarial Training
by: Amerehi, Fatemeh, et al.
Published: (2025)

Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP
by: Xu, Zhongxing, et al.
Published: (2024)

PROMISE: Prompt-Attentive Hierarchical Contrastive Learning for Robust Cross-Modal Representation with Missing Modalities
by: Chen, Jiajun, et al.
Published: (2025)

An Adaptive Tangent Feature Perspective of Neural Networks
by: LeJeune, Daniel, et al.
Published: (2023)

A Sober Look at the Robustness of CLIPs to Spurious Features
by: Wang, Qizhou, et al.
Published: (2024)

Multimodal Federated Learning With Missing Modalities through Feature Imputation Network
by: Poudel, Pranav, et al.
Published: (2025)

Understanding Domain Generalization: A Noise Robustness Perspective
by: Qiao, Rui, et al.
Published: (2024)

Bridging the Modality Gap in Roadside LiDAR: A Training-Free Vision-Language Model Framework for Vehicle Classification
by: Li, Yiqiao, et al.
Published: (2026)

Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining
by: Shechter, Mikey, et al.
Published: (2025)

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
by: Schrodi, Simon, et al.
Published: (2024)

Break a Lag: Triple Exponential Moving Average for Enhanced Optimization
by: Peleg, Roi, et al.
Published: (2023)

Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion
by: Cho, Minkyoung, et al.
Published: (2024)

Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation
by: Reza, Md Kaykobad, et al.
Published: (2023)

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
by: Yaras, Can, et al.
Published: (2024)

Feature-Space Smoothing: Certified Robustness of Deep Representations
by: Xia, Song, et al.
Published: (2026)

BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
by: Zhang, Jingfeng, et al.
Published: (2023)

Spatio-temporal Prompting Network for Robust Video Feature Extraction
by: Sun, Guanxiong, et al.
Published: (2024)

Robust Novelty Detection through Style-Conscious Feature Ranking
by: Smeu, Stefan, et al.
Published: (2023)

Understanding Adversarial Robustness from Feature Maps of Convolutional Layers
by: Xu, Cong, et al.
Published: (2022)

DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities
by: Lu, Jueqing, et al.
Published: (2025)

Recurrent Neural Networks for Still Images
by: Dmitri, et al.
Published: (2024)

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
by: Mannes, Mahmoud
Published: (2026)