{"total":89,"rows":[{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225,"area":"diffusion"},{"id":"2510.15301","title":"Latent Diffusion Model without Variational Autoencoder","created":"2025-10-17","cited_by_count":88,"area":"diffusion"},{"id":"2502.14831","title":"Improving the Diffusability of Autoencoders","created":"2025-02-20","cited_by_count":80,"area":"diffusion"},{"id":"2508.00413","title":"DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space","created":"2025-08-01","cited_by_count":47,"area":"diffusion"},{"id":"2504.16064","title":"Boosting Generative Image Modeling via Joint Image-Feature Synthesis","created":"2025-04-22","cited_by_count":45,"area":"diffusion"},{"id":"2509.25162","title":"AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models","created":"2025-09-29","cited_by_count":36,"area":"diffusion"},{"id":"2602.11401","title":"Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation","created":"2026-02-11","cited_by_count":36,"area":"diffusion"},{"id":"2506.21170","title":"Cosmos: Compressed and Smooth Latent Space for Text Diffusion Modeling","created":"2025-06-26","cited_by_count":25,"area":"diffusion"},{"id":"2503.06132","title":"USP: Unified Self-Supervised Pretraining for Image Generation and Understanding","created":"2025-03-08","cited_by_count":24,"area":"diffusion"},{"id":"2512.17909","title":"Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing","created":"2025-12-19","cited_by_count":22,"area":"diffusion"},{"id":"2510.01378","title":"Selective Underfitting in Diffusion Models","created":"2025-10-01","cited_by_count":18,"area":"diffusion"},{"id":"2507.13162","title":"Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models","created":"2025-07-17","cited_by_count":17,"area":"wm"},{"id":"2510.18457","title":"VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models","created":"2025-10-21","cited_by_count":17,"area":"diffusion"},{"id":"2601.18111","title":"Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting","created":"2026-01-26","cited_by_count":15,"area":null},{"id":"2603.05630","title":"Making Reconstruction FID Predictive of Diffusion Generation FID","created":"2026-03-05","cited_by_count":13,"area":"diffusion"},{"id":"2512.11749","title":"SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder","created":"2025-12-12","cited_by_count":12,"area":"diffusion"},{"id":"2512.05394","title":"Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability","created":"2025-12-05","cited_by_count":11,"area":"diffusion"},{"id":"2511.22249","title":"Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective","created":"2025-11-27","cited_by_count":10,"area":"diffusion"},{"id":"2602.08620","title":"Improving Reconstruction of Representation Autoencoder","created":"2026-02-09","cited_by_count":9,"area":"diffusion"},{"id":"2605.07915","title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","created":"2026-05-08","cited_by_count":9,"area":"diffusion"},{"id":"2509.25180","title":"DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space","created":"2025-09-29","cited_by_count":8,"area":"diffusion"},{"id":"2506.00433","title":"Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2509.05441","title":"Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2512.04084","title":"SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2603.14645","title":"Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion","created":"2026-03-15","cited_by_count":7,"area":"diffusion"},{"id":"2504.17219","title":"Enhancing Variational Autoencoders with Smooth Robust Latent Encoding","created":"2025-04-24","cited_by_count":6,"area":"diffusion"},{"id":"2506.19839","title":"Improving Progressive Generation with Decomposable Flow Matching","created":"2025-06-24","cited_by_count":6,"area":"diffusion"},{"id":"2508.17756","title":"SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling","created":"2025-08-25","cited_by_count":6,"area":"diffusion"},{"id":"2512.07778","title":"Distribution Matching Variational AutoEncoder","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2602.19461","title":"Laplacian Multi-scale Flow Matching for Generative Modeling","created":"2026-02-23","cited_by_count":6,"area":"diffusion"},{"id":"2606.03578","title":"Diffusing in the Right Space: A Systematic Study of Latent Diffusability","created":"2026-06-02","cited_by_count":6,"area":"diffusion"},{"id":"2504.09789","title":"On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise","created":"2025-04-14","cited_by_count":5,"area":"diffusion"},{"id":"2512.11225","title":"VFMF: World Modeling by Forecasting Vision Foundation Model Features","created":"2025-12-12","cited_by_count":5,"area":"wm"},{"id":"2512.16636","title":"REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion","created":"2025-12-18","cited_by_count":5,"area":"diffusion"},{"id":"2602.02092","title":"FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space","created":"2026-02-02","cited_by_count":5,"area":"diffusion"},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2509.25275","title":"VoiceBridge: General Speech Restoration with One-step Latent Bridge Models","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2506.07863","title":"VIVAT: Virtuous Improving VAE Training through Artifact Mitigation","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2510.07961","title":"Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2510.26782","title":"Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models","created":"2025-10-30","cited_by_count":3,"area":"wm"},{"id":"2512.05140","title":"FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation","created":"2025-12-01","cited_by_count":3,"area":"diffusion"},{"id":"2512.09923","title":"Splatent: Splatting Diffusion Latents for Novel View Synthesis","created":"2025-12-10","cited_by_count":3,"area":"diffusion"},{"id":"2605.05781","title":"Steering Visual Generation in Unified Multimodal Models with Understanding Supervision","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2505.15263","title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2510.08409","title":"Optimal Stopping in Latent Diffusion Models","created":"2025-10-09","cited_by_count":2,"area":"diffusion"},{"id":"2601.05028","title":"Approximate Equivariance via Projection-based Regularisation","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.26357","title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","created":"2026-03-27","cited_by_count":2,"area":"diffusion"},{"id":"2605.15193","title":"Aligning Latent Geometry for Spherical Flow Matching in Image Generation","created":"2026-05-14","cited_by_count":2,"area":"diffusion"},{"id":"2605.21981","title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","created":"2026-05-21","cited_by_count":2,"area":"diffusion"},{"id":"2510.19887","title":"Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery","created":"2025-10-22","cited_by_count":1,"area":"diffusion"},{"id":"2510.23530","title":"Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.12083","title":"RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model","created":"2025-12-12","cited_by_count":1,"area":"diffusion"},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.17087","title":"The Learnability Gap in Medical Latent Diffusion","created":"2026-05-16","cited_by_count":1,"area":"diffusion"},{"id":"2605.18390","title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.16396","title":"SP$^3$: Spherical Priors for Plug-and-Play Restoration","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2608.05798","title":"KVAE: Family of Tokenizers for Multimodal Generative Models","created":"2026-08-06","cited_by_count":1,"area":"diffusion"},{"id":"2509.06068","title":"Home-made Diffusion Model from Scratch to Hatch","created":"2025-09-07","cited_by_count":0,"area":"diffusion"},{"id":"2509.20481","title":"Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.00974","title":"JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.15172","title":"Complex variational autoencoders admit K\\\"ahler structure","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.22848","title":"Unconditional flow-based time series generation with equivariance-regularised latent spaces","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.11807","title":"PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts","created":"2026-02-12","cited_by_count":0,"area":"diffusion"},{"id":"2603.05925","title":"RAC: Rectified Flow Auto Coder","created":"2026-03-06","cited_by_count":0,"area":"diffusion"},{"id":"2603.07246","title":"LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.09408","title":"Reviving ConvNeXt for Efficient Convolutional Diffusion Models","created":"2026-03-10","cited_by_count":0,"area":"diffusion"},{"id":"2603.23179","title":"Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion","created":"2026-03-24","cited_by_count":0,"area":"diffusion"},{"id":"2604.02751","title":"Understanding Latent Diffusability via Fisher Geometry","created":"2026-04-03","cited_by_count":0,"area":"diffusion"},{"id":"2604.11089","title":"Structured State-Space Regularization for Generation-Friendly Image Tokenization","created":"2026-04-13","cited_by_count":0,"area":"ssm"},{"id":"2604.17492","title":"Coevolving Representations in Joint Image-Feature Diffusion","created":"2026-04-19","cited_by_count":0,"area":"diffusion"},{"id":"2605.08633","title":"Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.13470","title":"Twincher: Bijective Representation Learning for Robust Inversion of Continuous Systems","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18267","title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","created":"2026-05-18","cited_by_count":0,"area":"diffusion"},{"id":"2606.00635","title":"How Neural Losses Shape VAE Latents","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07036","title":"STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation","created":"2026-06-05","cited_by_count":0,"area":"diffusion"},{"id":"2606.09273","title":"EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Models","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"id":"2606.12263","title":"VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models","created":"2026-06-10","cited_by_count":0,"area":"diffusion"},{"id":"2607.19332","title":"ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling","created":"2026-07-21","cited_by_count":0,"area":"diffusion"},{"id":"2608.01306","title":"SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.23864","title":"AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.24088","title":"A Latent Distribution Perspective on Evaluating and Improving Latent Generative Models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.28473","title":"On the Diffusibility of High-Dimensional Latents","created":"2026-09-23","cited_by_count":0,"area":"diffusion"},{"id":"2609.37080","title":"LDM-is-AE: Latent Diffusion Model is an Auto-Encoder for End-to-End Image Generation","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.02203","title":"Embedding Prediction Helps Image Generation","created":"2026-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2610.03959","title":"LatentQuant: Preserving the Policy-Facing Latent Contract under NVFP4 VAE Quantization","created":"2026-10-02","cited_by_count":0,"area":"wm"},{"id":"2610.12843","title":"APEX: Asynchronous Prefix Denoising for Extreme Compression","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16204","title":"VGGA: Geometry-Grounded Autoencoder for Video Generation","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.16759","title":"Image Tokenizers Should Be Trained Between Images","created":"2026-10-12","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}