@chloesu07.bsky.social
📤 13
📥 25
📝 0
CS PhD student @ Harvard/Kempner Institute
reposted by
Isabel Papadimitriou
about 2 months ago
Are there conceptual directions in VLMs that transcend modality? Check out our COLM oral spotlight 🔦 paper! We use SAEs to analyze the multimodality of linear concepts in VLMs with
@chloesu07.bsky.social
,
@thomasfel.bsky.social
,
@shamkakade.bsky.social
and Stephanie Gil
arxiv.org/abs/2504.11695
1
25
7
reposted by
Kempner Institute at Harvard University
7 months ago
New in the Deeper Learning blog: Kempner researchers show how VLMs speak the same semantic language across images and text.
bit.ly/KempnerVLM
by
@isabelpapad.bsky.social
,Chloe Huangyuan Su,
@thomasfel.bsky.social
, Stephanie Gil, and
@shamkakade.bsky.social
#AI
#ML
#VLMs
#SAEs
loading . . .
Interpreting the Linear Structure of Vision-Language Model Embedding Spaces - Kempner Institute
Using sparse autoencoders, the authors show that vision-language embeddings boil down to a small, stable dictionary of single-modality concepts that snap together into cross-modal bridges. This resear...
https://bit.ly/KempnerVLM
0
9
3
you reached the end!!
feeds!
log in
