Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
This short paper introduces an abstraction called Think Again Networks (ThinkNet) which can be applied to any state-dependent function (such as a recurrent neural network).
arXiv comments
redacted experiments on language modeling due to evaluation error
Very cool to see the effectiveness of recurrence on ARC. For those interested in recurrence, here are other works that leverage a similar approach for other types of problems: Language modeling: Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach…
Very cool to see the effectiveness of recurrence on ARC. For those interested in recurrence, here are other works that leverage a similar approach for other types of problems: Language modeling: Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach…
atrudeauView on HNParent context