# Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Ability

arXiv: https://arxiv.org/abs/2506.01970 · HTML: https://mlsanity.com/paper/2506.01970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 13 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 12 of 12)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2203.04571/) (2022)
- [The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning](https://mlsanity.com/paper/2007.04212/) (2020)
- [In-Context Analogical Reasoning with Pre-Trained Language Models](https://mlsanity.com/paper/2305.17626/) (2023)
- [LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning](https://mlsanity.com/paper/2502.11176/) (2025)
- [SAViR-T: Spatially Attentive Visual Reasoning with Transformers](https://mlsanity.com/paper/2206.09265/) (2022)
- [Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems](https://mlsanity.com/paper/2307.07734/) (2023)
- [Solving the Clustering Reasoning Problems by Modeling a Deep-Learning-Based Probabilistic Model](https://mlsanity.com/paper/2403.03173/) (2024)
- [Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability](https://mlsanity.com/paper/2403.03190/) (2024)

## Abstract (arXiv)

This paper thoroughly investigates the challenges of enhancing AI's abstract reasoning capabilities, with a particular focus on Raven's Progressive Matrices (RPM) tasks involving complex human-like concepts. Firstly, it dissects the empirical reality that traditional end-to-end RPM-solving models heavily rely on option pool configurations, highlighting that this dependency constrains the model's reasoning capabilities. To address this limitation, the paper proposes the Johnny architecture - a novel representation space-based framework for RPM-solving. Through the synergistic operation of its Representation Extraction Module and Reasoning Module, Johnny significantly enhances reasoning performance by supplementing primitive negative option configurations with a learned representation space. Furthermore, to strengthen the model's capacity for capturing positional relationships among local features, the paper introduces the Spin-Transformer network architecture, accompanied by a lightweight Straw Spin-Transformer variant that reduces computational overhead through parameter sharing and attention mechanism optimization. Experimental evaluations demonstrate that both Johnny and Spin-Transformer achieve superior performance on RPM tasks, offering innovative methodologies for advancing AI's abstract reasoning capabilities.