Research map / Vision-language and multimodal / Human and embodied modeling

Representing Part-Whole Hierarchy with Nested Neuronal Coherence

NeurIPS 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a framework representing part-whole hierarchies in neural networks via nested neuronal coherence, inspired by the neural syntax hypothesis.

Problem

Neural networks struggle to represent part-whole hierarchical structure in visual scenes, which human vision handles flexibly.

Approach

Represents hierarchical part-whole relationships through nested neuronal coherence, a continuous and distributed dynamical mechanism, motivated by the neural syntax hypothesis.

Closest papers by meaning

• Flexible Context-Driven Sensory Processing in Dynamical Vision Models (NeurIPS 2024 · similarity 0.86)
• Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers (ICLR 2025 · similarity 0.85)
• Neural networks are more modular than single neurons suggest (NeurIPS 2026 · similarity 0.85)
• Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning (ICLR 2025 · similarity 0.85)
• Learning from Pattern Completion: Self-supervised Controllable Generation (NeurIPS 2024 · similarity 0.85)
• Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts (NeurIPS 2025 · similarity 0.85)