I am particularly interested in the approach proposed in the PersonaMem-V2 paper, where a 4B model is trained to generate personalized responses via reinforcement learning. I wonder if there are any plans to open-source the associated code? Thank you very much!
I am particularly interested in the approach proposed in the PersonaMem-V2 paper, where a 4B model is trained to generate personalized responses via reinforcement learning. I wonder if there are any plans to open-source the associated code? Thank you very much!