Excited to share that POSSM has been accepted to #NeurIPS2025! See you in San Diego ๐๏ธ
Nanda H Krishna
New preprint! ๐ง ๐ค
How do we build neural decoders that are:
โก๏ธ fast enough for real-time use
๐ฏ accurate across diverse tasks
๐ generalizable to new sessions, subjects, and even species?
We present POSSM, a hybrid SSM architecture that optimizes for all three of these axes!
๐งต1/7