{"total":19,"rows":[{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2606.15553","title":"Distilling Drifting Transformers with Representation Autoencoders","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2608.05000","title":"Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2608.13556","title":"V-RAE: Rethinking Video Latent Spaces for Generation","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2606.26016","title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.08676","title":"UniSpace: Unified Visual Representation and Scalable Multimodal Modeling","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2609.31620","title":"FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2607.22148","title":"dRAE: Representation Autoencoder with Hyper-Spherical Codes","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.00626","title":"Where Does Generative Difficulty Reside? An Empirical Study of Target Representations","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.24981","title":"GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.37330","title":"The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37775","title":"HiRAE: Hierarchical Representation Autoencoding with Residual Budgets","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39315","title":"Rethinking Generative Image Compression at Extremely Low Bitrates","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39635","title":"SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00600","title":"Just Align $\\bm{x}$: Aligning Predictions, Not Representations","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04781","title":"Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.09242","title":"Pooling Representation Autoencoders for Efficient Diffusion","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13299","title":"Decoding Register Tokens Preserves Global Scene Details","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17015","title":"DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}