{"total":55,"rows":[{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"area":null},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99,"area":null},{"id":"2409.16211","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","created":"2024-09-24","cited_by_count":98,"area":"diffusion"},{"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":"2512.16760","title":"Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future","created":"2025-12-18","cited_by_count":33,"area":"vla"},{"id":"2506.09110","title":"CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model","created":"2025-06-10","cited_by_count":28,"area":null},{"id":"2405.20786","title":"Stratified Avatar Generation from Sparse Observations","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2506.05289","title":"Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","created":"2025-06-05","cited_by_count":20,"area":null},{"id":"2505.17011","title":"Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space","created":"2025-05-22","cited_by_count":16,"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":"2509.10140","title":"Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2602.09024","title":"Autoregressive Image Generation with Masked Bit Modeling","created":"2026-02-09","cited_by_count":9,"area":null},{"id":"2409.08518","title":"Anytime Continual Learning for Open Vocabulary Classification","created":"2024-09-13","cited_by_count":8,"area":null},{"id":"2501.03078","title":"Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks","created":"2025-01-06","cited_by_count":8,"area":null},{"id":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2506.15078","title":"Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Study","created":"2025-06-18","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":"2404.01697","title":"Preventing Model Collapse in Gaussian Process Latent Variable Models","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2407.04939","title":"Balance of Number of Embedding and their Dimensions in Vector Quantization","created":"2024-07-06","cited_by_count":4,"area":null},{"id":"2507.14534","title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","created":"2025-07-19","cited_by_count":4,"area":null},{"id":"2405.14222","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2506.02599","title":"Assessing the Completeness of Traffic Scenario Categories for Automated Highway Driving Functions via Cluster-based Analysis","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2508.09857","title":"OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better","created":"2025-08-13","cited_by_count":3,"area":"mllm"},{"id":"2405.17016","title":"$\\text{Di}^2\\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation","created":"2024-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2408.04262","title":"CoBooM: Codebook Guided Bootstrapping for Medical Image Representation Learning","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2505.11334","title":"MARRS: Masked Autoregressive Unit-based Reaction Synthesis","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.22952","title":"Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantization","created":"2025-06-28","cited_by_count":2,"area":null},{"id":"2508.06588","title":"Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2508.10719","title":"Exploiting Discriminative Codebook Prior for Autoregressive Image Generation","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2502.08253","title":"Multi-View Oriented GPLVM: Expressiveness and Efficiency","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2601.10169","title":"CtD: Composition through Decomposition in Emergent Communication","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.17133","title":"VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.25249","title":"Semantic-Aware Prefix Learning for Token-Efficient Image Generation","created":"2026-03-26","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":"2608.14656","title":"P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2609.33129","title":"Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy","created":"2026-09-27","cited_by_count":1,"area":"diffusion"},{"id":"2410.17700","title":"Scalable Random Feature Latent Variable Models","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2503.10832","title":"Dual Codebook VQ: Enhanced Image Reconstruction with Reduced Codebook Size","created":"2025-03-13","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":"2504.18059","title":"POET: Prompt Offset Tuning for Continual Human Action Adaptation","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2506.20214","title":"UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation","created":"2025-06-25","cited_by_count":0,"area":"mllm"},{"id":"2507.14097","title":"Generative AI-Driven High-Fidelity Human Motion Simulation","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2510.04220","title":"MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2601.00222","title":"LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2601.01577","title":"HanoiWorld : A Joint Embedding Predictive Architecture BasedWorld Model for Autonomous Vehicle Controller","created":"2026-01-04","cited_by_count":0,"area":"wm"},{"id":"2602.01140","title":"Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.07889","title":"Efficient Anti-exploration via VQVAE and Fuzzy Clustering in Offline Reinforcement Learning","created":"2026-02-08","cited_by_count":0,"area":"offlinerl"},{"id":"2602.21319","title":"Uncertainty-Aware Diffusion Model for Multimodal Highway Trajectory Prediction via DDIM Sampling","created":"2026-02-24","cited_by_count":0,"area":"diffusion"},{"id":"2603.16964","title":"Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.06870","title":"Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.13517","title":"ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.11363","title":"NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.26774","title":"StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}