Tootfinder

Maximally-Informative Retrieval for State Space Model Generation
Evan Becker, Benjamin Bowman, Matthew Trager, Tian Yu Liu, Luca Zancato, Wei Xia, Stefano Soatto
https://arxiv.org/abs/2506.12149

Maximally-Informative Retrieval for State Space Model Generation
Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, but data not deemed important during training is forgotten, and information outside that training set cannot be made use of. Processing an entire dataset at inference time is infeasible due to the bounded nature of model resources (e.g. context size in transformers or states in state space models), meaning we must resor…