ResearchTrend.AI
Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation

Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation

Jitian Zhao
Chenghui Li
Frederic Sala
Karl Rohe
ArXiv (abs)PDFHTML

Papers citing "Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation"

2 / 2 papers shown
Title
SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models
SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models
Sepehr Kazemi Ranjbar
Kumail Alhamoud
Marzyeh Ghassemi
VLM
20
0
0
15 Nov 2025
Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
Interpreting ResNet-based CLIP via Neuron-Attention Decomposition
Edmund Bu
Yossi Gandelsman
68
0
0
24 Sep 2025