zhanpeng_zhou

• zhanpeng_zhou 11 Jan 2024 11:52 UTC

  6 points

  0

  in reply to: Bogdan Ionut Cirstea’s comment on: Go­ing Beyond Lin­ear Mode Con­nec­tivity: The Lay­er­wise Lin­ear Fea­ture Connectivity

  Great comments! Actually, we have made some progress in linking task arithmetic with our NeurIPS 2023 results and we are working on a new manuscript to introduce our new results. Hope our new paper could be released soon.

• zhanpeng_zhou 21 Jul 2023 2:05 UTC

  2 points

  0

  in reply to: Charlie Steiner’s comment on: Go­ing Beyond Lin­ear Mode Con­nec­tivity: The Lay­er­wise Lin­ear Fea­ture Connectivity

  Actually, someone found the Mode Connectivity in ViT (a quite larger NN I thought). Not sure if LLFC will be still satisfied on ViT but it worth a try. As for the pruned network, I believe that pruned network still holds the LLFC. (I think you refer the LLFC as “weak additivity”, right?)
  

Go­ing Beyond Lin­ear Mode Con­nec­tivity: The Lay­er­wise Lin­ear Fea­ture Connectivity