{"total":75,"rows":[{"id":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304,"area":null},{"id":"2504.08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","created":"2025-04-11","cited_by_count":57,"area":null},{"id":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2511.04675","title":"InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation","created":"2025-11-06","cited_by_count":45,"area":null},{"id":"2503.16430","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation","created":"2025-03-20","cited_by_count":29,"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":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2410.04081","title":"Epsilon-VAE: Denoising as Visual Decoding","created":"2024-10-05","cited_by_count":16,"area":null},{"id":"2412.16326","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2504.02612","title":"Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13,"area":null},{"id":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12,"area":null},{"id":"2510.09012","title":"Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy","created":"2025-10-10","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":"2508.05599","title":"WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction","created":"2025-08-07","cited_by_count":9,"area":null},{"id":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2602.09024","title":"Autoregressive Image Generation with Masked Bit Modeling","created":"2026-02-09","cited_by_count":9,"area":null},{"id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","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":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2601.01535","title":"Improving Flexible Image Tokenizers for Autoregressive Image Generation","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2505.10562","title":"End-to-End Vision Tokenizer Tuning","created":"2025-05-15","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":"2509.26469","title":"DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2412.02632","title":"Scaling Image Tokenizers with Grouped Spherical Quantization","created":"2024-12-03","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":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.14041","title":"BitDance: Scaling Autoregressive Generative Models with Binary Tokens","created":"2026-02-15","cited_by_count":4,"area":null},{"id":"2605.11704","title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2606.18249","title":"Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification","created":"2026-06-16","cited_by_count":4,"area":null},{"id":"2503.06623","title":"Transforming Weather Data from Pixel to Latent Space","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2503.08377","title":"Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2603.17546","title":"ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2505.22394","title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2512.08537","title":"Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.06602","title":"Scaling Speech Tokenizers with Diffusion Autoencoders","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2603.16373","title":"Semantic One-Dimensional Tokenizer for Image Reconstruction and Generation","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2505.21680","title":"multivariateGPT: a decoder-only transformer for multivariate categorical and numeric data","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2508.11183","title":"Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.06311","title":"WindFM: An Open-Source Foundation Model for Zero-Shot Wind Power Forecasting","created":"2025-09-08","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":"2601.14246","title":"Soft Tail-dropping for Adaptive Visual Tokenization","created":"2026-01-20","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":"2603.05299","title":"WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.14591","title":"Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.11192","title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.30317","title":"VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation","created":"2026-05-28","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":"2505.13542","title":"GANCompress: GAN-Enhanced Neural Image Compression with Binary Spherical Quantization","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.09612","title":"Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive","created":"2025-07-13","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":"2511.12181","title":"MixAR: Mixture Autoregressive Image Generation","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.01831","title":"Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.03811","title":"Progressive Checkerboards for Autoregressive Multiscale Image Generation","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.15045","title":"VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.05171","title":"Modality-Aware and Anatomical Vector-Quantized Autoencoding for Multimodal Brain MRI","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.19750","title":"C2P-VAR: Continual and Compositional Personalization in Visual Autoregressive Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.19972","title":"Block-Sphere Vector Quantization","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.29316","title":"CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.04461","title":"ChannelTok: Efficient Flexible-Length Vision Tokenization","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.13558","title":"Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.25548","title":"Concept Removal for Frontier Image Generative Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27627","title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.29282","title":"ScaleErasure: Inference-Time Minimal Intervention for Precise Concept Erasure in Next-Scale Autoregressive Image Generation","created":"2026-06-28","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":"2608.03127","title":"DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05727","title":"LILAC: An Idempotent Neural Speech Codec","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.28082","title":"Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models","created":"2026-08-28","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":"2609.31816","title":"Relational Compression: A Framework for Relational Fidelity in Constrained Representations","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.39451","title":"ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image Compression","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.10497","title":"QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation","created":"2026-10-07","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}