# PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models

arXiv: https://arxiv.org/abs/2606.23086 · HTML: https://mlsanity.com/paper/2606.23086/

## 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 9 of its 13 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 9 of 9)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Structural Pruning for Diffusion Models](https://mlsanity.com/paper/2305.10924/) (2023)

## Abstract (arXiv)

Latent diffusion models achieve strong generative performance by operating in a compressed latent space produced by a variational autoencoder (VAE). However, it remains unclear whether all latent channels contribute equally to the diffusion process, or whether significant redundancy exists. We introduce PeLAP-A (Adaptive Latent Pruning for Diffusion), a lightweight framework that augments a standard latent diffusion pipeline with a learnable channel-wise importance predictor. A two-layer MLP operating on globally pooled latent features produces a soft mask that suppresses unimportant latent channels before they enter the denoising UNet. The entire system is trained jointly on CIFAR-10 under a combined diffusion, reconstruction, and sparsity loss. Experiments reveal a striking result: under aggressive sparsity regularization (lambda = 0.01), the importance predictor drives all latent channels to near-zero yet the denoising UNet achieves lower diffusion loss (0.0236 vs. 0.0240) and lower VAE reconstruction MSE (22.59 vs. 24.67) compared to the unpruned baseline. We term this the sparsity collapse phenomenon and provide an analysis of why it occurs and what it reveals about the information requirements of latent diffusion models. These findings constitute an exploratory study of sparsity dynamics in latent diffusion training, and demonstrate that denoising UNets can remain remarkably robust to latent channel suppression even under aggressive regularization. Code is available at: https://github.com/kissasium/PeLAP-A.git.