There's also the problem that there is currently a huge transformer monoculture in the AI space. Everything gets better if you throw transformers at the problem.
If you had worked on anything other than a transformer based architecture post 2016, such as Mamba or RWKV, you would have wasted your time.
Mamba 3 is the third iteration and somehow I doubt that it will catch on.
If you had worked on anything other than a transformer based architecture post 2016, such as Mamba or RWKV, you would have wasted your time.
Mamba 3 is the third iteration and somehow I doubt that it will catch on.