{"total":96,"rows":[{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163,"area":null},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136,"area":"wm"},{"id":"2511.20645","title":"PixelDiT: Pixel Diffusion Transformers for Image Generation","created":"2025-11-25","cited_by_count":83,"area":"diffusion"},{"id":"2504.08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","created":"2025-04-11","cited_by_count":57,"area":null},{"id":"2505.02831","title":"No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves","created":"2025-05-05","cited_by_count":56,"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":"2509.25162","title":"AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models","created":"2025-09-29","cited_by_count":36,"area":"diffusion"},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2510.06590","title":"Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer","created":"2025-10-08","cited_by_count":28,"area":null},{"id":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27,"area":null},{"id":"2510.10575","title":"UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation","created":"2025-10-12","cited_by_count":23,"area":null},{"id":"2507.15856","title":"Latent Denoising Makes Good Tokenizers","created":"2025-07-21","cited_by_count":20,"area":null},{"id":"2507.02608","title":"Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation","created":"2025-07-03","cited_by_count":19,"area":"diffusion"},{"id":"2504.10567","title":"H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models","created":"2025-04-14","cited_by_count":13,"area":"diffusion"},{"id":"2507.04947","title":"DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer","created":"2025-07-07","cited_by_count":13,"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":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12,"area":null},{"id":"2505.22391","title":"Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation","created":"2025-05-28","cited_by_count":11,"area":"diffusion"},{"id":"2507.09984","title":"Latent Diffusion Models with Masked AutoEncoders","created":"2025-07-14","cited_by_count":11,"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":"2503.08354","title":"Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis","created":"2025-03-11","cited_by_count":10,"area":null},{"id":"2508.05599","title":"WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction","created":"2025-08-07","cited_by_count":9,"area":null},{"id":"2509.01109","title":"GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation","created":"2025-09-01","cited_by_count":9,"area":null},{"id":"2602.05951","title":"Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching","created":"2026-02-05","cited_by_count":9,"area":"diffusion"},{"id":"2603.09241","title":"RAE-NWM: Navigation World Model in Dense Visual Representation Space","created":"2026-03-10","cited_by_count":9,"area":"wm"},{"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":"2509.23736","title":"HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation","created":"2025-09-28","cited_by_count":8,"area":null},{"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":"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":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2512.09924","title":"Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning","created":"2025-12-10","cited_by_count":7,"area":"lr"},{"id":"2601.22904","title":"Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation","created":"2026-01-30","cited_by_count":7,"area":"diffusion"},{"id":"2511.13019","title":"MeanFlow Transformers with Representation Autoencoders","created":"2025-11-17","cited_by_count":6,"area":"diffusion"},{"id":"2512.20619","title":"SemanticGen: Video Generation in Semantic Space","created":"2025-12-23","cited_by_count":6,"area":"diffusion"},{"id":"2601.01535","title":"Improving Flexible Image Tokenizers for Autoregressive Image Generation","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2603.22125","title":"DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment","created":"2026-03-23","cited_by_count":6,"area":"diffusion"},{"id":"2505.12053","title":"VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption","created":"2025-05-17","cited_by_count":5,"area":"diffusion"},{"id":"2506.21022","title":"Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2509.24935","title":"Scalable GANs with Transformers","created":"2025-09-29","cited_by_count":5,"area":null},{"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":"2512.18184","title":"Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching","created":"2025-12-20","cited_by_count":5,"area":"diffusion"},{"id":"2505.20535","title":"Rotary Masked Autoencoders are Versatile Learners","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2512.13421","title":"RecTok: Reconstruction Distillation along Rectified Flow","created":"2025-12-15","cited_by_count":4,"area":"diffusion"},{"id":"2601.05823","title":"Boosting Latent Diffusion Models via Disentangled Representation Alignment","created":"2026-01-09","cited_by_count":4,"area":"diffusion"},{"id":"2601.17124","title":"iFSQ: Improving FSQ for Image Generation with 1 Line of Code","created":"2026-01-23","cited_by_count":4,"area":"diffusion"},{"id":"2602.04220","title":"Adaptive 1D Video Diffusion Autoencoder","created":"2026-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2604.11331","title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","created":"2026-04-13","cited_by_count":3,"area":"diffusion"},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2506.05240","title":"Aligning Latent Spaces with Flow Priors","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2506.14373","title":"Discrete JEPA: Learning Discrete Token Representations without Reconstruction","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2603.29634","title":"MacTok: Robust Continuous Tokenization for Image Generation","created":"2026-03-31","cited_by_count":2,"area":null},{"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":"2605.25294","title":"Geometry-Aware Image Flow Matching","created":"2026-05-24","cited_by_count":2,"area":"diffusion"},{"id":"2510.06673","title":"Heptapod: Language Modeling on Visual Signals","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2511.16117","title":"Decoupling Complexity from Scale in Latent Diffusion Model","created":"2025-11-20","cited_by_count":1,"area":"diffusion"},{"id":"2601.07773","title":"Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?","created":"2026-01-12","cited_by_count":1,"area":"diffusion"},{"id":"2603.21085","title":"Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models","created":"2026-03-22","cited_by_count":1,"area":"diffusion"},{"id":"2604.01545","title":"RAE-AR: Taming Autoregressive Models with Representation Autoencoders","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.07340","title":"TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.24885","title":"VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations","created":"2026-04-27","cited_by_count":1,"area":"diffusion"},{"id":"2605.14569","title":"Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.05552","title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.19651","title":"BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation","created":"2026-06-17","cited_by_count":1,"area":"diffusion"},{"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":"2606.32039","title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.18510","title":"DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer","created":"2026-07-20","cited_by_count":1,"area":"diffusion"},{"id":"2607.22531","title":"Twins: Learn to Predict Unified Representations with Focal Loss","created":"2026-07-24","cited_by_count":1,"area":"diffusion"},{"id":"2504.00952","title":"Personalized Federated Training of Diffusion Models with Privacy Guarantees","created":"2025-04-01","cited_by_count":0,"area":"diffusion"},{"id":"2506.18270","title":"Adaptive Mask-guided K-space Diffusion for Accelerated MRI Reconstruction","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2511.17372","title":"Quantum Masked Autoencoders for Vision Learning","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2601.22837","title":"NativeTok: Native Visual Tokenization for Improved Image Generation","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.10702","title":"UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.11089","title":"Structured State-Space Regularization for Generation-Friendly Image Tokenization","created":"2026-04-13","cited_by_count":0,"area":"ssm"},{"id":"2605.27696","title":"Structure over Pixels: Learning Variable-Length Visual Programs","created":"2026-05-26","cited_by_count":0,"area":null},{"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":"2606.20076","title":"Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers","created":"2026-06-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.11516","title":"LoopVAE: Recurrent Depth Across Scales for Visual Tokenization","created":"2026-09-10","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":"2609.28206","title":"UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation","created":"2026-09-23","cited_by_count":0,"area":"diffusion"},{"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":"2609.37495","title":"MotionMaestro: Masked Tokenization for Unified Motion Generation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.39222","title":"DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2609.39315","title":"Rethinking Generative Image Compression at Extremely Low Bitrates","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":"2610.00686","title":"SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation","created":"2026-09-30","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":"2610.13181","title":"MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement","created":"2026-10-09","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}