{"total":20,"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":"2406.11837","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","created":"2024-06-17","cited_by_count":68,"area":null},{"id":"2305.11718","title":"Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization","created":"2023-05-19","cited_by_count":60,"area":null},{"id":"2312.11529","title":"Efficient and Scalable Graph Generation through Iterative Local Expansion","created":"2023-12-14","cited_by_count":36,"area":null},{"id":"2310.05400","title":"Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers","created":"2023-10-09","cited_by_count":33,"area":null},{"id":"2212.03185","title":"Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis","created":"2022-12-06","cited_by_count":31,"area":null},{"id":"2303.10406","title":"3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process","created":"2023-03-18","cited_by_count":25,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2305.01319","title":"Long-Term Rhythmic Video Soundtracker","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2312.17397","title":"Classifier-free graph diffusion for molecular property targeting","created":"2023-12-28","cited_by_count":14,"area":null},{"id":"2305.10841","title":"GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2403.01124","title":"Text-guided Explorable Image Super-resolution","created":"2024-03-02","cited_by_count":9,"area":null},{"id":"2301.02736","title":"Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition","created":"2023-01-06","cited_by_count":5,"area":null},{"id":"2411.17784","title":"HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2408.08459","title":"JPEG-LM: LLMs as Image Generators with Canonical Codec Representations","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2412.15674","title":"PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2405.20743","title":"Trajectory Forecasting through Low-Rank Adaptation of Discrete Latent Codes","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2407.18290","title":"Several questions of visual generation in 2024","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2509.19592","title":"Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2604.22847","title":"Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes","created":"2026-04-22","cited_by_count":0,"area":null}],"next_cursor":null}