Decomposing stimulus-specific sensory neural information via diffusion models
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
To understand sensory coding, we must ask not only how much information neurons encode, but also what that information is about. This requires decomposing mutual information into contributions from individual stimuli and stimulus features: a fundamentally ill-posed problem with infinitely many possible solutions. We address this by introducing three core axioms, additivity, positivity, and locality that any meaningful stimulus-wise decomposition should satisfy. We then derive a decomposition that meets all three criteria and remains tractable for high-dimensional stimuli. Our decomposition can be efficiently estimated using diffusion models, allowing for scaling up to complex, structured and naturalistic stimuli. Applied to a model of visual neurons, our method quantifies how specific stimuli and features contribute to encoded information. Our approach provides a scalable, interpretable tool for probing representations in both biological and artificial neural systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 12 of its 38 references that are in the map. First posted on arXiv 16 May 2025.
Builds on
12 of 38 references.
Closest ancestors · 2
Same direction, newest first
- 2023Interpretable Diffusion via Information Decomposition12 Oct
- 2020Denoising Diffusion Probabilistic Models19 Jun
Other references · 10
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
- 2020Solving Linear Inverse Problems Using the Prior Implicit in a Denoisercited by 79
- 2021Estimating High Order Gradients of the Data Distribution by Denoisingcited by 64
- 2024Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariancecited by 44
- 2021Neural tuning and representational geometrycited by 31
- 2017Neural system identification for large populations separating "what" and "where"cited by 28
- 2024DiffusionPID: Interpreting Diffusion via Partial Information Decompositioncited by 16
- 2016Information-Theoretic Bounds and Approximations in Neural Population Codingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025On the Separability of Information in Diffusion Models
- 2026Toward a mechanistic understanding of inference in visual cortex and diffusion models
- 2025Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion
- 2022A Measure of the Complexity of Neural Representations based on Partial Information Decomposition
- 2026Causal Interpretation of Neural Network Computations with Contribution Decomposition
- 2022Semantic Brain Decoding: from fMRI to conceptually similar image reconstruction of visual stimuli
- 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
- 2025From superposition to sparse codes: interpretable representations in neural networks