Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) Usha Bhalla Harvard University
–Neural Information Processing Systems
In this work, we show that the semantic structure of CLIP's latent space can be
Neural Information Processing Systems
Nov-19-2025, 22:42:43 GMT
- Country:
- Europe
- Greece (0.04)
- Switzerland > Zürich
- Zürich (0.14)
- United Kingdom > England
- Staffordshire (0.04)
- North America > United States (0.14)
- Europe
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.93)
- Research Report
- Industry:
- Health & Medicine (0.67)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.93)
- Natural Language > Text Processing (1.00)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Machine Learning > Neural Networks
- Data Science (0.93)
- Artificial Intelligence
- Information Technology