FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation

Guangsheng Bao, Hongbo Zhang, Han Cui, Ke Sun, Yanbin Zhao, Juncai He, Yue Zhang

FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation: 1 upvotes on Hugging Face Daily Papers, #34 of 57 papers on 2026-05-14. Day-by-day upvote history.

Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning. We propose FAAST, a forward-only associative adaptation method that analytically compiles labeled examples into fast weights in a single pass. By eliminating memory or context dependence, FAAST achieves constant-time inference and decouples task adaptation from pretrained representation. Across image classification and language modeling benchmarks, FAAST matches or exceeds backprop-based adaptation while reducing adaptation time by over 90% and is competitive to memory/context-based adaptation while saving memory usage by up to 95%. These results demonstrate FAAST as a highly efficient, scalable solution for supervised task adaptation, particularly for resource-constrained models. We release the code and models at https://github.com/baoguangsheng/faast.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.