Name | Description | URL | Research paper on mechanistic interpretability of Vision-Language Models (VLMs) | Uses CLIP as the vision encoder in the study | Discusses methods to identify and isolate circuits within the models | Citation Count | Add column | |
|---|---|---|---|---|---|---|---|---|
1 | ||||||||
2 | ||||||||
3 | ||||||||
4 | ||||||||
5 | ||||||||
1 | ||||||||
2 | ||||||||
3 | ||||||||
4 | ||||||||
5 | ||||||||