Cover Image

Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Chuan, Venhoff, Constantin, Joseph, Sonia, Xiao, Fanyi, Scherer, Stefan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Visual Representations Map to Language Feature Space in Multimodal LLMs
by: Venhoff, Constantin, et al.
Published: (2025)

Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
by: Hufe, Lorenz, et al.
Published: (2025)

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
by: Morelli, Fabian, et al.
Published: (2026)

Interpreting CLIP with Hierarchical Sparse Autoencoders
by: Zaigrajew, Vladimir, et al.
Published: (2025)

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
by: Bhalla, Usha, et al.
Published: (2024)

BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
by: Liang, Siyuan, et al.
Published: (2026)

SparseContrast: Dynamic Sparse Attention for Efficient and Accurate Contrastive Learning in Medical Imaging
by: Prasad, Paarth, et al.
Published: (2026)

Interpretability Transfer from Language to Vision via Sparse Autoencoders
by: Kravets, Alexey, et al.
Published: (2026)

Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
by: Li, Jiachen, et al.
Published: (2023)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
by: Liang, Siyuan, et al.
Published: (2023)

CoRe: Joint Optimization with Contrastive Learning for Medical Image Registration
by: Kats, Eytan, et al.
Published: (2026)

Interpreting the Second-Order Effects of Neurons in CLIP
by: Gandelsman, Yossi, et al.
Published: (2024)

CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values
by: Koleilat, Taha, et al.
Published: (2025)

Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts
by: Kubota, Yugo, et al.
Published: (2024)

PowerCLIP: Powerset Alignment for Contrastive Pre-Training
by: Kawamura, Masaki, et al.
Published: (2025)

$β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
by: Zohra, Fatimah, et al.
Published: (2025)

ContrastDiagnosis: Enhancing Interpretability in Lung Nodule Diagnosis Using Contrastive Learning
by: Wang, Chenglong, et al.
Published: (2024)

Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
by: Ro, Yusung, et al.
Published: (2026)

EntityCLIP: Entity-Centric Image-Text Matching via Multimodal Attentive Contrastive Learning
by: Wang, Yaxiong, et al.
Published: (2024)

CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP
by: Tang, Zhenchen, et al.
Published: (2024)

Towards Understanding Multimodal Fine-Tuning: Spatial Features
by: Naghashyar, Lachin, et al.
Published: (2026)

Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning
by: Chen, Sherry X., et al.
Published: (2025)

MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations
by: Avci, Mehmet Yigit, et al.
Published: (2025)

CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis
by: Sundaram, Aravindan, et al.
Published: (2024)

Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
by: Yeo, Wei Jie, et al.
Published: (2025)

CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
by: Li, Yukun, et al.
Published: (2024)

FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text
by: Wang, Bingchao, et al.
Published: (2025)

WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
by: Ning, Shan, et al.
Published: (2026)

MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations Theory
by: Condez, Ana Carolina, et al.
Published: (2025)

CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
by: Xiao, Linhui, et al.
Published: (2023)

ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
by: Wang, Jingyun, et al.
Published: (2024)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
by: Bai, Jiawang, et al.
Published: (2023)

DeCLIP: Decoding CLIP representations for deepfake localization
by: Smeu, Stefan, et al.
Published: (2024)

Sparse-to-Sparse Training of Diffusion Models
by: Oliveira, Inês Cardoso, et al.
Published: (2025)

BotaCLIP: Contrastive Learning for Botany-Aware Representation of Earth Observation Data
by: Cerna, Selene, et al.
Published: (2025)

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
by: Nakka, Krishna Kanth
Published: (2025)

Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
by: Sammani, Fawaz, et al.
Published: (2024)

Quantifying and Enabling the Interpretability of CLIP-like Models
by: Madasu, Avinash, et al.
Published: (2024)

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling
by: Wang, Xinze, et al.
Published: (2025)

Ultrasound-CLIP: Semantic-Aware Contrastive Pre-training for Ultrasound Image-Text Understanding
by: Jin, Jiayun, et al.
Published: (2026)