{"total":50,"rows":[{"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":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2412.02692","title":"Scalable Image Tokenization with Index Backpropagation Quantization","created":"2024-12-03","cited_by_count":44,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2402.11843","title":"WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection","created":"2024-02-19","cited_by_count":31,"area":null},{"id":"2406.07119","title":"T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text","created":"2024-06-11","cited_by_count":30,"area":null},{"id":"2412.06782","title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction","created":"2024-12-09","cited_by_count":27,"area":null},{"id":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23,"area":null},{"id":"2501.03120","title":"CAT: Content-Adaptive Image Tokenization","created":"2025-01-06","cited_by_count":21,"area":null},{"id":"2403.10071","title":"Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2503.10406","title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","created":"2025-03-13","cited_by_count":16,"area":null},{"id":"2412.09607","title":"Spectral Image Tokenizer","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2404.13372","title":"HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression","created":"2024-04-20","cited_by_count":14,"area":null},{"id":"2503.07076","title":"NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2409.05606","title":"CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization","created":"2024-09-09","cited_by_count":13,"area":null},{"id":"2412.01762","title":"XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation","created":"2024-12-02","cited_by_count":12,"area":null},{"id":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12,"area":null},{"id":"2509.19406","title":"TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding","created":"2025-09-23","cited_by_count":12,"area":null},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"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":"2505.02192","title":"DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization","created":"2025-05-04","cited_by_count":10,"area":null},{"id":"2501.04975","title":"V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer","created":"2025-01-09","cited_by_count":9,"area":null},{"id":"2503.17760","title":"CODA: Repurposing Continuous VAEs for Discrete Tokenization","created":"2025-03-22","cited_by_count":8,"area":null},{"id":"2603.12267","title":"EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2507.01945","title":"LongAnimation: Long Animation Generation with Dynamic Global-Local Memory","created":"2025-07-02","cited_by_count":6,"area":null},{"id":"2406.10553","title":"A Comprehensive Taxonomy and Analysis of Talking Head Synthesis: Techniques for Portrait Generation, Driving Mechanisms, and Editing","created":"2024-06-15","cited_by_count":5,"area":null},{"id":"2509.26469","title":"DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2605.00503","title":"End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2311.17425","title":"SpeechAct: Towards Generating Whole-body Motion from Speech","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2501.18328","title":"Virtual Full-stack Scanning of Brain MRI via Imputing Any Quantised Code","created":"2025-01-30","cited_by_count":4,"area":null},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2505.16845","title":"Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2407.11913","title":"Quantised Global Autoencoder: A Holistic Approach to Representing Visual Data","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2501.02521","title":"Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization","created":"2025-01-05","cited_by_count":3,"area":null},{"id":"2411.10281","title":"Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2507.04559","title":"MambaVideo for Discrete Video Tokenization with Channel-Split Quantization","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2501.09187","title":"Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2508.13515","title":"2D Gaussians Meet Visual Tokenizer","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2512.06609","title":"Training-Free Vector Quantization via Gaussian VAEs","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2607.15933","title":"Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.19575","title":"VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2406.13735","title":"StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic Images","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2410.10234","title":"LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2412.01046","title":"Improving Detail in Pluralistic Image Inpainting with Feature Dequantization","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2503.16425","title":"Tokenize Image as a Set","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2503.17155","title":"D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2510.08449","title":"Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction","created":"2025-10-09","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":"2605.26089","title":"Channel-wise Vector Quantization","created":"2026-05-25","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}],"next_cursor":null}