{"total":80,"rows":[{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2504.01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","created":"2025-04-02","cited_by_count":54,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2508.02739","title":"Kronos: A Foundation Model for the Language of Financial Markets","created":"2025-08-02","cited_by_count":26,"area":null},{"id":"2503.06764","title":"SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation","created":"2025-03-09","cited_by_count":21,"area":null},{"id":"2503.13026","title":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model","created":"2025-03-17","cited_by_count":20,"area":"mllm"},{"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":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11,"area":null},{"id":"2602.08984","title":"Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models","created":"2026-02-09","cited_by_count":11,"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":"2509.10140","title":"Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2511.23386","title":"VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction","created":"2025-11-28","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":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2504.04405","title":"Universal Item Tokenization for Transferable Generative Recommendation","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2511.20565","title":"DINO-Tok: Adapting DINO for Visual Tokenizers","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2505.24291","title":"Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion","created":"2025-05-30","cited_by_count":5,"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":"2511.06863","title":"VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling","created":"2025-11-10","cited_by_count":5,"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":"2504.11434","title":"Enhancing Out-of-Distribution Detection with Extended Logit Normalization","created":"2025-04-15","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":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2604.02289","title":"Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation","created":"2026-04-02","cited_by_count":3,"area":"mllm"},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2507.18897","title":"HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling","created":"2025-07-25","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":"2511.14184","title":"GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2511.23469","title":"Visual Generation Tuning","created":"2025-11-28","cited_by_count":2,"area":"mllm"},{"id":"2601.02776","title":"UniSRCodec: Unified and Low-Bitrate Single Codebook Codec with Sub-Band Reconstruction","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2601.10124","title":"VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2606.11096","title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2510.06673","title":"Heptapod: Language Modeling on Visual Signals","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.16273","title":"MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2601.17438","title":"UniGRec: Unified Generative Recommendation with Soft Identifiers for End-to-End Optimization","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","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":"2602.18896","title":"Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization","created":"2026-02-21","cited_by_count":1,"area":"diffusion"},{"id":"2603.16435","title":"VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.17052","title":"Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2606.27313","title":"ViQ: Text-Aligned Visual Quantized Representations at Any Resolution","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2606.30113","title":"SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance","created":"2026-06-29","cited_by_count":1,"area":"vla"},{"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":"2609.29456","title":"Dense Coverage, Sparse Refinement: Byte-Constrained Cooperative Perception","created":"2026-09-24","cited_by_count":1,"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":"2503.16425","title":"Tokenize Image as a Set","created":"2025-03-20","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":"2509.16577","title":"Learned Digital Over-the-Air Computing for Federated Edge Learning","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2509.22161","title":"Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.13331","title":"Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.20224","title":"DuoTok: Source-Aware Dual-Track Music Tokenization for Vocal-Accompaniment Generation","created":"2025-11-25","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":"2512.19777","title":"Learned Digital Codes for Over-the-Air Computation in Federated Edge Learning","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2601.22244","title":"Is Hierarchical Quantization Essential for Optimal Reconstruction?","created":"2026-01-29","cited_by_count":0,"area":null},{"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":"2602.16086","title":"LGQ: Learnable Geometric Quantization for Image Tokenization","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.18904","title":"PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2603.06766","title":"HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.22304","title":"Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2604.03850","title":"Collapse-Free Prototype Readout Layer for Transformer Encoders","created":"2026-04-04","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":"2605.14333","title":"InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation","created":"2026-05-14","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":"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":"2606.12940","title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.08643","title":"BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.20981","title":"Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence","created":"2026-07-23","cited_by_count":0,"area":"moe"},{"id":"2607.22148","title":"dRAE: Representation Autoencoder with Hyper-Spherical Codes","created":"2026-07-24","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":"2609.03641","title":"Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.24691","title":"What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization","created":"2026-09-21","cited_by_count":0,"area":"diffusion"},{"id":"2609.26774","title":"StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.36866","title":"S2T-Unet: A Structure-to-Style Framework for Inter-Modality MRI Translation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04651","title":"GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding","created":"2026-10-03","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},{"id":"2610.18481","title":"ProTok: Unified Protein Tokenization via Modular Multi-Codebook Quantization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}