{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/all-roads-lead-to-rome-exploring","title":"All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models","arxiv_id":"2407.13449","date":"2024-07-18","proceeding":null,"authors":["Charumathi Badrinath","Usha Bhalla","Alex Oesterling","Suraj Srinivas","Himabindu Lakkaraju"],"abstract":"Do different generative image models secretly learn similar underlying representations? We investigate this by measuring the latent space similarity of four different models: VAEs, GANs, Normalizing Flows (NFs), and Diffusion Models (DMs). Our methodology involves training linear maps between frozen latent spaces to \"stitch\" arbitrary pairs of encoders and decoders and measuring output-based and probe-based metrics on the resulting \"stitched'' models. Our main findings are that linear maps between latent spaces of performant models preserve most visual information even when latent sizes differ; for CelebA models, gender is the most similarly represented probe-able attribute. Finally we show on an NF that latent space representations converge early in training.","url_abs":"https://arxiv.org/abs/2407.13449v1","url_pdf":"https://arxiv.org/pdf/2407.13449v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"all-roads-lead-to-rome-exploring","repo_url":"https://github.com/charumathib/thesis-latent-spaces","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"attribute","task_name":"Attribute"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}