{"total":159,"rows":[{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651,"area":null},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648,"area":null},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400,"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":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2312.03701","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","created":"2023-12-06","cited_by_count":98,"area":null},{"id":"2502.09509","title":"EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling","created":"2025-02-13","cited_by_count":89,"area":null},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"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":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2501.07730","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","created":"2025-01-13","cited_by_count":50,"area":null},{"id":"2502.17437","title":"Fractal Generative Models","created":"2025-02-24","cited_by_count":46,"area":null},{"id":"2412.02692","title":"Scalable Image Tokenization with Index Backpropagation Quantization","created":"2024-12-03","cited_by_count":44,"area":null},{"id":"2408.01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","created":"2024-08-02","cited_by_count":42,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2406.10450","title":"TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation","created":"2024-06-15","cited_by_count":35,"area":null},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"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":"2401.14391","title":"Rethinking Patch Dependence for Masked Autoencoders","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2404.02845","title":"Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation","created":"2024-04-03","cited_by_count":28,"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":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23,"area":null},{"id":"2412.12032","title":"FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning","created":"2024-12-16","cited_by_count":23,"area":null},{"id":"2512.16922","title":"Next-Embedding Prediction Makes Strong Vision Learners","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2410.10511","title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2512.19693","title":"The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding","created":"2025-12-22","cited_by_count":22,"area":null},{"id":"2304.03977","title":"EMP-SSL: Towards Self-Supervised Learning in One Training Epoch","created":"2023-04-08","cited_by_count":19,"area":null},{"id":"2501.15420","title":"Visual Generation Without Guidance","created":"2025-01-26","cited_by_count":17,"area":null},{"id":"2401.03321","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","created":"2024-01-06","cited_by_count":16,"area":null},{"id":"2601.16148","title":"ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion","created":"2026-01-22","cited_by_count":16,"area":null},{"id":"2405.10812","title":"VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling","created":"2024-05-13","cited_by_count":15,"area":null},{"id":"2409.02979","title":"Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors","created":"2024-09-04","cited_by_count":15,"area":null},{"id":"2411.04406","title":"Image Understanding Makes for A Good Tokenizer for Image Generation","created":"2024-11-07","cited_by_count":15,"area":null},{"id":"2307.16605","title":"VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation","created":"2023-07-28","cited_by_count":14,"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":"2410.09347","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment","created":"2024-10-12","cited_by_count":14,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"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":"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":"2502.07239","title":"Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation","created":"2025-02-11","cited_by_count":12,"area":null},{"id":"2406.07398","title":"Visual Representation Learning with Stochastic Frame Prediction","created":"2024-06-11","cited_by_count":10,"area":null},{"id":"2407.11294","title":"COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2412.13111","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","created":"2024-12-17","cited_by_count":9,"area":null},{"id":"2504.08959","title":"MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer","created":"2025-04-11","cited_by_count":9,"area":null},{"id":"2505.07812","title":"Continuous Visual Autoregressive Generation via Score Maximization","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2305.14135","title":"Reparo: Loss-Resilient Generative Codec for Video Conferencing","created":"2023-05-23","cited_by_count":8,"area":null},{"id":"2310.03734","title":"Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency","created":"2023-10-05","cited_by_count":8,"area":null},{"id":"2411.04079","title":"Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generation","created":"2024-11-06","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":"2503.17760","title":"CODA: Repurposing Continuous VAEs for Discrete Tokenization","created":"2025-03-22","cited_by_count":8,"area":null},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","cited_by_count":8,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2311.10801","title":"Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools","created":"2023-11-17","cited_by_count":7,"area":null},{"id":"2312.09812","title":"Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2404.00513","title":"Transformer based Pluralistic Image Completion with Reduced Information Loss","created":"2024-03-31","cited_by_count":7,"area":null},{"id":"2405.15622","title":"LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2405.16847","title":"TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2407.09087","title":"On the Role of Discrete Tokenization in Visual Representation Learning","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2504.16953","title":"TVC: Tokenized Video Compression with Ultra-Low Bit Rate","created":"2025-04-22","cited_by_count":7,"area":null},{"id":"2310.01251","title":"Generating 3D Brain Tumor Regions in MRI using Vector-Quantization Generative Adversarial Networks","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2310.17188","title":"Blind Image Super-resolution with Rich Texture-Aware Codebooks","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2410.16257","title":"Elucidating the design space of language models for image generation","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2504.10188","title":"Efficient Generative Model Training via Embedded Representation Warmup","created":"2025-04-14","cited_by_count":6,"area":null},{"id":"2604.12887","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2309.11661","title":"Neural Image Compression Using Masked Sparse Visual Representation","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2310.16318","title":"Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2410.14672","title":"BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities","created":"2024-10-18","cited_by_count":5,"area":null},{"id":"2501.03229","title":"Gaussian Masked Autoencoders","created":"2025-01-06","cited_by_count":5,"area":null},{"id":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2505.16195","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2306.07792","title":"Rethinking Polyp Segmentation from an Out-of-Distribution Perspective","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2308.07301","title":"A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis","created":"2023-08-14","cited_by_count":4,"area":null},{"id":"2407.09533","title":"Video Occupancy Models","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2506.00698","title":"Concept-Centric Token Interpretation for Vector-Quantized Generative Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2507.01652","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2508.05162","title":"X-MoGen: Unified Motion Generation across Humans and Animals","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2512.20107","title":"UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2301.12058","title":"Aerial Image Object Detection With Vision Transformer Detector (ViTDet)","created":"2023-01-28","cited_by_count":3,"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":"2407.14911","title":"Self-supervised transformer-based pre-training method with General Plant Infection dataset","created":"2024-07-20","cited_by_count":3,"area":null},{"id":"2411.13602","title":"Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2508.08991","title":"Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2602.04202","title":"VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2310.04010","title":"Excision And Recovery: Visual Defect Obfuscation Based Self-Supervised Anomaly Detection Strategy","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2403.09290","title":"SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survival","created":"2024-03-14","cited_by_count":2,"area":null},{"id":"2405.15268","title":"ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.02883","title":"ARINAR: Bi-Level Autoregressive Feature-by-Feature Generative Models","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2505.03426","title":"Phenotype-Guided Generative Model for High-Fidelity Cardiac MRI Synthesis: Advancing Pretraining and Clinical Applications","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2510.17171","title":"Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2510.21003","title":"Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2511.23334","title":"Markovian Scale Prediction: A New Era of Visual Autoregressive Generation","created":"2025-11-28","cited_by_count":2,"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}],"next_cursor":"100"}