Hi Everyone, In the reading discussion this week, we will discuss: “Multimodal Neurons in Pretrained Text-Only Transformers” This paper is about multimodal neurons in text-only transformer MLPs and how these neurons consistently translate image semantics into language. The reading discussion is at 4-5 pm on Feb 16ht this Friday. You may attend the reading discussion in Room 366 in the Data & Decision Building, or on Zoom (https://virginiatech.zoom.us/j/5961845863) Best Regards, Mo Link to paper: https://openaccess.thecvf.com/content/ICCV2023W/CLVL/papers/Schwettmann_Mult... [preview.png] Schwettmann_Multimodal_Neurons_in_Pretrained_Text-Only_Transformers_ICCVW_2023_paperhttps://openaccess.thecvf.com/content/ICCV2023W/CLVL/papers/Schwettmann_Mult... PDF Document · 16.9 MBhttps://openaccess.thecvf.com/content/ICCV2023W/CLVL/papers/Schwettmann_Mult...