Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability
This work addresses the problem of machine abstract reasoning for AI systems, presenting an incremental improvement over existing baselines.
The paper tackles visual abstract reasoning by introducing a method that explicitly models the distribution of correct solutions, leading to improved performance on RPM and Bongard-Logo tasks with enhanced interpretability.
Visual abstract reasoning is core to image processing. We present Valen, a unified probability-highlighting baseline that excels on both RPM (progression) and Bongard-Logo (clustering) tasks. Analysing its internals, we find solvers implicitly treat each task as a distribution where primary samples fit and auxiliaries do not; hence the learning target is jointly shaped by both sets, not by correct solutions alone. To close the gap we first introduce Tine, an adversarial adapter that nudges Valen toward correct-solution density, but adversarial training is unstable. We therefore replace it with Funny, a fast Gaussian-mixture model that directly estimates the correct-solution density without adversarial games, and extend the same paradigm to SBR for progressive-pattern planning. Extensive experiments show explicit distribution planning is the key to stronger, interpretable abstract reasoning. Codes are available in: https://github.com/Yuanbeiming/Funny-Valen-Tine-Planning-Solution-Distribution-Enhances-Machine-Abstract-Reasoning-Ability