This paper proposes a new method to dynamically adjust the precision of weights in a small local model during decoding, and evaluates its effectiveness in improving accuracy. A practitioner might care about this approach if they want to improve the performance of their small local models, especially in scenarios where the output distribution is uncertain.
Firehose
Filtered to Papers, tagged “entropy-based decision making” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives