{"total":37,"rows":[{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648,"area":null},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302,"area":null},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161,"area":null},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75,"area":null},{"id":"2303.04743","title":"Vector Quantized Time Series Generation with a Bidirectional Prior Model","created":"2023-03-08","cited_by_count":50,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2212.07372","title":"Image Compression with Product Quantized Masked Image Modeling","created":"2022-12-14","cited_by_count":33,"area":null},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2406.10797","title":"STAR: Scale-wise Text-conditioned AutoRegressive image generation","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2302.05496","title":"MaskSketch: Unpaired Structure-guided Masked Image Generation","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2310.14400","title":"A Pytorch Reproduction of Masked Generative Image Transformer","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2501.15417","title":"AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement","created":"2025-01-26","cited_by_count":23,"area":null},{"id":"2404.09562","title":"{\\sigma}-GPTs: A New Approach to Autoregressive Models","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2503.13147","title":"Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing","created":"2025-03-17","cited_by_count":17,"area":null},{"id":"2409.00342","title":"AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation","created":"2024-08-31","cited_by_count":13,"area":null},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13,"area":null},{"id":"2410.03143","title":"ECHOPulse: ECG controlled echocardio-grams video generation","created":"2024-10-04","cited_by_count":9,"area":null},{"id":"2306.00763","title":"Learning Disentangled Prompts for Compositional Image Synthesis","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2411.06959","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2604.19141","title":"Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation","created":"2026-04-21","cited_by_count":5,"area":null},{"id":"2306.15561","title":"You Can Mask More For Extremely Low-Bitrate Image Compression","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2309.07945","title":"Masked Generative Modeling with Enhanced Sampling Scheme","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2503.08377","title":"Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2601.07218","title":"SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2407.09099","title":"Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2409.01591","title":"Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformers","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2511.12032","title":"Improved Masked Image Generation with Knowledge-Augmented Token Representations","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2601.14246","title":"Soft Tail-dropping for Adaptive Visual Tokenization","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2307.14701","title":"MIM-OOD: Generative Masked Image Modelling for Out-of-Distribution Detection in Medical Images","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2506.12035","title":"MARch\\'e: Fast Masked Autoregressive Image Generation with Cache-Aware Attention","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2510.12231","title":"BIGFix: Bidirectional Image Generation with Token Fixing","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2603.19570","title":"Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.19807","title":"Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.12724","title":"Inline Critic Steers Image Editing","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2610.03822","title":"Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstruction","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}