{"total":68,"rows":[{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"area":null},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82,"area":null},{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2307.15139","title":"Online Clustered Codebook","created":"2023-07-27","cited_by_count":55,"area":null},{"id":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2401.00365","title":"HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes","created":"2023-12-31","cited_by_count":27,"area":null},{"id":"2302.05917","title":"Vector Quantized Wasserstein Auto-Encoder","created":"2023-02-12","cited_by_count":22,"area":null},{"id":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2310.05718","title":"EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders","created":"2023-10-09","cited_by_count":16,"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":"2411.04406","title":"Image Understanding Makes for A Good Tokenizer for Image Generation","created":"2024-11-07","cited_by_count":15,"area":null},{"id":"2503.15475","title":"Cube: A Roblox View of 3D Intelligence","created":"2025-03-19","cited_by_count":15,"area":null},{"id":"2301.12811","title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","created":"2023-01-30","cited_by_count":14,"area":null},{"id":"2605.06548","title":"Continuous Latent Diffusion Language Model","created":"2026-05-07","cited_by_count":14,"area":"diffusion"},{"id":"2403.13015","title":"HyperVQ: MLR-based Vector Quantization in Hyperbolic Space","created":"2024-03-18","cited_by_count":13,"area":null},{"id":"2406.03234","title":"Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning","created":"2024-06-05","cited_by_count":11,"area":"deeprl"},{"id":"2303.00750","title":"StraIT: Non-autoregressive Generation with Stratified Image Transformer","created":"2023-03-01","cited_by_count":10,"area":"diffusion"},{"id":"2310.03004","title":"Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2507.07997","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","created":"2025-07-10","cited_by_count":9,"area":null},{"id":"2409.09253","title":"Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism","created":"2024-09-14","cited_by_count":8,"area":"lr"},{"id":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2310.09604","title":"Learning Hierarchical Features with Joint Latent Space Energy-Based Prior","created":"2023-10-14","cited_by_count":6,"area":null},{"id":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"area":null},{"id":"2509.13482","title":"Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization","created":"2025-09-16","cited_by_count":6,"area":null},{"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":"2506.21022","title":"Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2507.10566","title":"AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems","created":"2025-07-07","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":"2511.06863","title":"VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling","created":"2025-11-10","cited_by_count":5,"area":null},{"id":"2310.00277","title":"A Unified Framework for Generative Data Augmentation: A Comprehensive Survey","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2310.09382","title":"LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations","created":"2023-10-13","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":"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":"2504.02286","title":"Moment Quantization for Video Temporal Grounding","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2601.11183","title":"Democratizing planetary-scale analysis: An ultra-lightweight Earth embedding database for accurate and flexible global land monitoring","created":"2026-01-16","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":"2401.03341","title":"Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection","created":"2024-01-07","cited_by_count":2,"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":"2410.10180","title":"Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2506.14373","title":"Discrete JEPA: Learning Discrete Token Representations without Reconstruction","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2506.20040","title":"Cross-Layer Discrete Concept Discovery for Interpreting Language Models","created":"2025-06-24","cited_by_count":2,"area":"mechinterp"},{"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":"2305.15927","title":"Parameter Estimation in DAGs from Incomplete Data via Optimal Transport","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2309.02478","title":"Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview","created":"2023-09-05","cited_by_count":1,"area":null},{"id":"2411.16468","title":"Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency","created":"2024-11-25","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":"2602.02726","title":"Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery","created":"2026-02-02","cited_by_count":1,"area":"mechinterp"},{"id":"2602.17133","title":"VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation","created":"2026-02-19","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":"2409.13533","title":"Using High-Level Patterns to Estimate How Humans Predict a Robot will Behave","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2412.13917","title":"Speech Watermarking with Discrete Intermediate Representations","created":"2024-12-18","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":"2505.19470","title":"Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.09896","title":"A look at adversarial attacks on radio waveforms from discrete latent space","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.11511","title":"Task-Driven Discrete Representation Learning","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2512.01537","title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","created":"2025-12-01","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":"2601.12391","title":"Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene Generation","created":"2026-01-18","cited_by_count":0,"area":"diffusion"},{"id":"2601.22244","title":"Is Hierarchical Quantization Essential for Optimal Reconstruction?","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.02508","title":"Precoding-Oriented CSI Feedback Design with Mutual Information Regularized VQ-VAE","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.09277","title":"Mutual Information Collapse Explains Disentanglement Failure in $\\beta$-VAEs","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.07175","title":"Multiple Domain Generalization Using Category Information Independent of Domain Differences","created":"2026-04-08","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":"2609.02107","title":"A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.12067","title":"Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}