add paper link

Author: kashif

examples/research_projects/lpl/README.md

@@ -1,6 +1,6 @@
 # Latent Perceptual Loss (LPL) for Stable Diffusion XL
 
-This directory contains an implementation of Latent Perceptual Loss (LPL) for training Stable Diffusion XL models, based on the paper "Boosting Latent Diffusion with Perceptual Objectives" (Berrada et al., 2025). LPL is a perceptual loss that operates in the latent space of a VAE, helping to improve the quality and consistency of generated images by bridging the disconnect between the diffusion model and the autoencoder decoder.
+This directory contains an implementation of Latent Perceptual Loss (LPL) for training Stable Diffusion XL models, based on the paper: [Boosting Latent Diffusion with Perceptual Objectives](https://huggingface.co/papers/2411.04873) (Berrada et al., 2025). LPL is a perceptual loss that operates in the latent space of a VAE, helping to improve the quality and consistency of generated images by bridging the disconnect between the diffusion model and the autoencoder decoder.
 
 ## Overview