# Conformal Disentanglement and Latent-Space Curation: A Neural Framework for Perspective Synthesis, Differentiation and Targeted Generation

arXiv: https://arxiv.org/abs/2408.15344 · HTML: https://mlsanity.com/paper/2408.15344/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 27 Aug 2024.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Maximum Likelihood Training of Score-Based Diffusion Models](https://mlsanity.com/paper/2101.09258/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Diffusion Nets](https://mlsanity.com/paper/1506.07840/) (2015)
- [Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimation](https://mlsanity.com/paper/2310.14458/) (2023)
- [On the Parameter Combinations That Matter and on Those That do Not](https://mlsanity.com/paper/2110.06717/) (2021)
- [Probabilistic Learning on Manifolds (PLoM) with Partition](https://mlsanity.com/paper/2102.10894/) (2021)
- [A common variable minimax theorem for graphs](https://mlsanity.com/paper/2107.14747/) (2021)
- [Gappy local conformal auto-encoders for heterogeneous data fusion: in praise of rigidity](https://mlsanity.com/paper/2312.13155/) (2023)

## Built on by (most cited first, 1 of 1)

- [Neural Chaos: A Spectral Stochastic Neural Operator](https://mlsanity.com/paper/2502.11835/) (2025)

## Abstract (arXiv)

Many scientific and engineering problems involve observing a common phenomenon through multiple heterogeneous sensors or measurement modalities. Such observations typically contain both information shared across sensors, reflecting the underlying system, and sensor-specific or extraneous components arising from measurement processes or environmental effects. Disentangling these contributions is essential when sensor-independent observations are unavailable. We propose a neural autoencoder framework that explicitly separates shared and sensor-specific latent variables from multi-sensor data. The architecture enforces geometric independence between latent components through structural constraints and orthogonality-based regularization, yielding interpretable and disentangled representations. Building on this representation, we then introduce a latent-space generative methodology in which generative models are tuned/"restricted" on selected disentangled latent subspaces; we then constructively combine disentangled observed latent variables to conditionally synthesize new samples via trained decoders. This enables consistent data generation with prescribed shared (or sensor-specific) characteristics. It also supports cross-sensor inference by consistently sampling distributions over plausible measurements in unobserved modalities. We demonstrate the approach on several computational examples, showing effective disentanglement, targeted data generation, and modality imputation in heterogeneous sensing settings.