Research
2D Spatial Reasoning with Adaptive Neural Cellular Automata
arXiv:2610.08518v1 Announce Type: new Abstract: Many modern learning approaches are still struggling with spatial reasoning tasks, i.e. they lack the ability to utilize geometric information of percei
arXiv:2610.08518v1 Announce Type: new Abstract: Many modern learning approaches are still struggling with spatial reasoning tasks, i.e. they lack the ability to utilize geometric information of perceived entities and their spatial relation to each other to solve problems. We introduce a novel Adaptive Neural Cellular Automata (aNCA) architecture which uses deformable convolutions to dynamically adapt the perceptive field and iteratively reason over 2D spatial relations on grid-like data structures (e.g. images). Empirical results on public benchmarks show state of the art comprehensible results with high generalization abilities for solving image based puzzles like Sudoku or finding the shortest path in a maze.
Related
- Reasoning with Neural Cellular Automata
- SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
- SpatialSkill: Self-Evolving Skills for Cross-View Spatial Reasoning
- Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
Source: arXiv cs.CV | 2026-10-07