Cover Image

Interpreting the Second-Order Effects of Neurons in CLIP

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gandelsman, Yossi, Efros, Alexei A., Steinhardt, Jacob
Format:	Preprint
Published:	2024
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

Interpreting CLIP's Image Representation via Text-Based Decomposition
by: Gandelsman, Yossi, et al.
Published: (2023)

Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
by: Bu, Edmund, et al.
Published: (2025)

Vision Transformers Don't Need Trained Registers
by: Jiang, Nick, et al.
Published: (2025)

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

Interpreting the Weight Space of Customized Diffusion Models
by: Dravid, Amil, et al.
Published: (2024)

Synthesizing Moving People with 3D Control
by: Li, Boyi, et al.
Published: (2024)

The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering
by: Ekin, Yigit, et al.
Published: (2026)

Test-Time Training on Video Streams
by: Wang, Renhao, et al.
Published: (2023)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
by: Jiang, Nick, et al.
Published: (2024)

Learning Video Representations without Natural Videos
by: Yu, Xueyang, et al.
Published: (2024)

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
by: Bhattad, Anand, et al.
Published: (2025)

The More You See in 2D, the More You Perceive in 3D
by: Han, Xinyang, et al.
Published: (2024)

Steering CLIP's vision transformer with sparse autoencoders
by: Joseph, Sonia, et al.
Published: (2025)

Teaching Humans Subtle Differences with DIFFusion
by: Chiquier, Mia, et al.
Published: (2025)

GPS as a Control Signal for Image Generation
by: Feng, Chao, et al.
Published: (2025)

Continuous 3D Perception Model with Persistent State
by: Wang, Qianqian, et al.
Published: (2025)

An Empirical Study of Autoregressive Pre-training from Videos
by: Rajasegaran, Jathushan, et al.
Published: (2025)

Jailbreaking Vision-Language Models Through the Visual Modality
by: Azulay, Aharon, et al.
Published: (2026)

LLMs can see and hear without any training
by: Ashutosh, Kumar, et al.
Published: (2025)

IT$^3$: Idempotent Test-Time Training
by: Durasov, Nikita, et al.
Published: (2024)

Toon3D: Seeing Cartoons from New Perspectives
by: Weber, Ethan, et al.
Published: (2024)

COLMAP-Free 3D Gaussian Splatting
by: Fu, Yang, et al.
Published: (2023)

Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions
by: Möller, Lucas, et al.
Published: (2024)

Disentangled 3D Scene Generation with Layout Learning
by: Epstein, Dave, et al.
Published: (2024)

Diffusion Models as Data Mining Tools
by: Siglidis, Ioannis, et al.
Published: (2024)

It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
by: Harrington, Anne, et al.
Published: (2025)

Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
by: Koepke, A. Sophia, et al.
Published: (2026)

Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
by: Wang, Sheng-Yu, et al.
Published: (2024)

Fast Data Attribution for Text-to-Image Models
by: Wang, Sheng-Yu, et al.
Published: (2025)

Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
by: Qin, Chuan, et al.
Published: (2026)

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

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

Evaluating Multiview Object Consistency in Humans and Image Models
by: Bonnen, Tyler, et al.
Published: (2024)

Rethinking Patch Dependence for Masked Autoencoders
by: Fu, Letian, et al.
Published: (2024)

Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation
by: Ji, ZeBin, et al.
Published: (2026)

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

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
by: Gentile, Francesco, et al.
Published: (2026)

Interpreting Biomedical VLMs on High-Imbalance Out-of-Distributions: An Insight into BiomedCLIP on Radiology
by: Sadman, Nafiz, et al.
Published: (2025)

Video CLIP Model for Multi-View Echocardiography Interpretation
by: Takizawa, Ryo, et al.
Published: (2025)

Interpreting Neurons in Deep Vision Networks with Language Models
by: Bai, Nicholas, et al.
Published: (2024)