I am a graduate student at KAIST, supervised by Kimin Lee. Please checkout my homepage https://mintaywon.github.io/, if you’re interested!
Taywon Min
Karma: 0
I am a graduate student at KAIST, supervised by Kimin Lee. Please checkout my homepage https://mintaywon.github.io/, if you’re interested!
Thanks for the great work. I think that multimodal sparse auto encoders is a promising direction. Do you think it is possible / worthwhile to train SAEs on vla models like OpenVLA? I haven’t seen any related work training or interpreting action models using SAE work, and am curious of your thoughts.