MiX

Hi Mr Bart, Your distributed-llama is great! However, are there any clear instructions to set up the whole environment from scratch? I'm interested in your distributed-llama but I lack related...

Hello, first of all, I'm very pleased to be able to read your paper, it's a great work in multi-task learning research! But I have some questions while reading the...

Hey, I noticed that you utilized a modified encoder-decoder version of the LeNet in C.1.1 MultiMNIST in your paper. However, upon examining the code, I observed that only 2 fully...

Whether setting "--scale-y=True" will affect the performance of other methods like MGDA, IMTL?

1

Hi, as I noticed in your previous issue, you said "--scale-y=True" would affect FAMO's performance. Will it affect the other methods' performance, like MGDA, LS, or IMTL in your code?