Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability

TL;DR

This paper introduces a novel approach that improves machine abstract reasoning by explicitly modeling solution distributions, using a Gaussian-mixture model to enhance interpretability and performance on reasoning tasks.

Contribution

It proposes Funny, a Gaussian-mixture model, to replace adversarial training for better distribution estimation, significantly improving reasoning capabilities.

Findings

Explicit distribution planning boosts reasoning accuracy.

The Gaussian-mixture model outperforms adversarial methods.

Approach enhances interpretability of reasoning processes.

Abstract

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