{"total":315,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651,"area":null},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302,"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":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150,"area":null},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"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":"2504.11171","title":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","created":"2025-04-15","cited_by_count":104,"area":null},{"id":"2511.07820","title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","created":"2025-11-11","cited_by_count":101,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90,"area":null},{"id":"2501.10105","title":"Universal Actions for Enhanced Embodied Foundation Models","created":"2025-01-17","cited_by_count":82,"area":null},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"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":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76,"area":null},{"id":"2506.18123","title":"RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies","created":"2025-06-22","cited_by_count":64,"area":null},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53,"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":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"area":null},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45,"area":null},{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44,"area":null},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43,"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":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2504.04953","title":"M-Prometheus: A Suite of Open Multilingual LLM Judges","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34,"area":null},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"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":"2502.05512","title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System","created":"2025-02-08","cited_by_count":28,"area":null},{"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":"2503.05305","title":"Frequency Autoregressive Image Generation with Continuous Tokens","created":"2025-03-07","cited_by_count":27,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2405.15677","title":"SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction","created":"2024-05-24","cited_by_count":25,"area":null},{"id":"2403.09673","title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond","created":"2024-02-04","cited_by_count":23,"area":null},{"id":"2510.10575","title":"UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation","created":"2025-10-12","cited_by_count":23,"area":null},{"id":"2406.17957","title":"Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2410.03311","title":"Scaling Large Motion Models with Million-Level Human Motions","created":"2024-10-04","cited_by_count":22,"area":null},{"id":"2506.17774","title":"PhysiX: A Foundation Model for Physics Simulations","created":"2025-06-21","cited_by_count":22,"area":null},{"id":"2501.03120","title":"CAT: Content-Adaptive Image Tokenization","created":"2025-01-06","cited_by_count":21,"area":null},{"id":"2503.01428","title":"DLF: Extreme Image Compression with Dual-generative Latent Fusion","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2507.08441","title":"Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation","created":"2025-07-11","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":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2506.08257","title":"Highly Compressed Tokenizer Can Generate Without Training","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2411.17178","title":"LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization","created":"2024-11-26","cited_by_count":17,"area":null},{"id":"2512.03018","title":"AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry","created":"2025-12-02","cited_by_count":17,"area":null},{"id":"2410.03437","title":"Zebra: In-Context Generative Pretraining for Solving Parametric PDEs","created":"2024-10-04","cited_by_count":16,"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":"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":"2411.04406","title":"Image Understanding Makes for A Good Tokenizer for Image Generation","created":"2024-11-07","cited_by_count":15,"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":"2503.00089","title":"Protein Structure Tokenization: Benchmarking and New Recipe","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2602.04215","title":"OAT: Ordered Action Tokenization","created":"2026-02-04","cited_by_count":15,"area":null},{"id":"2412.17726","title":"VidTwin: Video VAE with Decoupled Structure and Dynamics","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2503.07076","title":"NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2404.10282","title":"Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning","created":"2024-04-16","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":"2503.17074","title":"Zero-Shot Styled Text Image Generation, but Make It Autoregressive","created":"2025-03-21","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":"2506.03863","title":"STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization","created":"2025-06-04","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":"2411.18447","title":"Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2407.15835","title":"dMel: Speech Tokenization made Simple","created":"2024-07-22","cited_by_count":11,"area":null},{"id":"2411.16681","title":"Factorized Visual Tokenization and Generation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2503.00507","title":"Projection Head is Secretly an Information Bottleneck","created":"2025-03-01","cited_by_count":11,"area":null},{"id":"2504.03639","title":"Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions","created":"2025-04-04","cited_by_count":11,"area":null},{"id":"2507.02358","title":"Hita: Holistic Tokenizer for Autoregressive Image Generation","created":"2025-07-03","cited_by_count":11,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2405.15840","title":"Learning the Language of Protein Structure","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2405.16435","title":"Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning","created":"2024-05-26","cited_by_count":10,"area":null},{"id":"2411.16550","title":"Representation Collapsing Problems in Vector Quantization","created":"2024-11-25","cited_by_count":10,"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":"2508.07863","title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","created":"2025-08-11","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":"2410.01912","title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation","created":"2024-10-02","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":"2505.23660","title":"D-AR: Diffusion via Autoregressive Models","created":"2025-05-29","cited_by_count":9,"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":"2512.18181","title":"MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation","created":"2025-12-20","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":"2403.16883","title":"GLAD: Improving Latent Graph Generative Modeling with Simple Quantization","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2407.03495","title":"Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations","created":"2024-07-03","cited_by_count":8,"area":null},{"id":"2410.15765","title":"SeisLM: a Foundation Model for Seismic Waveforms","created":"2024-10-21","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":"2511.23402","title":"Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning","created":"2025-11-28","cited_by_count":8,"area":null},{"id":"2512.16975","title":"InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2412.10208","title":"Efficient Generative Modeling with Residual Vector Quantization-Based Tokens","created":"2024-12-13","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":"2507.10547","title":"Quantize-then-Rectify: Efficient VQ-VAE Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2509.09836","title":"CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio","created":"2025-09-11","cited_by_count":7,"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":"2603.12267","title":"EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2607.08741","title":"ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation","created":"2026-07-09","cited_by_count":7,"area":null}],"next_cursor":"100"}