C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions

arXiv:2604.13521v1 Announce Type: cross Abstract: Neural network models with latent recurrent processing, where identical layers are recursively applied to the latent state, have gained attention as promising models for performing reasoning tasks. A strength of such models is that they enable test-time scaling, where the models can enhance their performance in the test phase without additional training. Models such as the Hierarchical Reasoning Model (HRM) and Artificial Kuramoto Oscillatory Neu