{"ID":2896458,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06613","arxiv_id":"2507.06613","title":"Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation","abstract":"Disentangled and interpretable latent representations in generative models typically come at the cost of generation quality. The $β$-VAE framework introduces a hyperparameter $β$ to balance disentanglement and reconstruction quality, where setting $β\u003e 1$ introduces an information bottleneck that favors disentanglement over sharp, accurate reconstructions. To address this trade-off, we propose a novel generative modeling framework that leverages a range of $β$ values to learn multiple corresponding latent representations. First, we obtain a slew of representations by training a single variational autoencoder (VAE), with a new loss function that controls the information retained in each latent representation such that the higher $β$ value prioritize disentanglement over reconstruction fidelity. We then, introduce a non-linear diffusion model that smoothly transitions latent representations corresponding to different $β$ values. This model denoises towards less disentangled and more informative representations, ultimately leading to (almost) lossless representations, enabling sharp reconstructions. Furthermore, our model supports sample generation without input images, functioning as a standalone generative model. We evaluate our framework in terms of both disentanglement and generation quality. Additionally, we observe smooth transitions in the latent spaces with respect to changes in $β$, facilitating consistent manipulation of generated outputs.","short_abstract":"Disentangled and interpretable latent representations in generative models typically come at the cost of generation quality. The $β$-VAE framework introduces a hyperparameter $β$ to balance disentanglement and reconstruction quality, where setting $β\u003e 1$ introduces an information bottleneck that favors disentanglement...","url_abs":"https://arxiv.org/abs/2507.06613","url_pdf":"https://arxiv.org/pdf/2507.06613v1","authors":"[\"Anshuk Uppal\",\"Yuhta Takida\",\"Chieh-Hsin Lai\",\"Yuki Mitsufuji\"]","published":"2025-07-09T07:29:41Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Variational Autoencoder\"]","has_code":false}