{"total":440,"rows":[{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023,"area":"diffusion"},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864,"area":"wm"},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665,"area":"vla"},{"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":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288,"area":"diffusion"},{"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":"2505.17589","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","created":"2025-05-23","cited_by_count":150,"area":"diffusion"},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132,"area":"diffusion"},{"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":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"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":"2409.16211","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","created":"2024-09-24","cited_by_count":98,"area":"diffusion"},{"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":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"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":"2505.13934","title":"RLVR-World: Training World Models with Reinforcement Learning","created":"2025-05-20","cited_by_count":40,"area":"wm"},{"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":"2503.11056","title":"Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization","created":"2025-03-14","cited_by_count":36,"area":"diffusion"},{"id":"2502.15672","title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling","created":"2025-02-21","cited_by_count":35,"area":"wm"},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"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":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"area":null},{"id":"2505.14682","title":"UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation","created":"2025-05-20","cited_by_count":32,"area":"mllm"},{"id":"2407.00114","title":"OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents","created":"2024-06-27","cited_by_count":30,"area":"vla"},{"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":"2502.05236","title":"Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance","created":"2025-02-07","cited_by_count":27,"area":"alignment"},{"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":"2505.16687","title":"One-Step Diffusion-Based Image Compression with Semantic Distillation","created":"2025-05-22","cited_by_count":26,"area":"diffusion"},{"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":"2406.02328","title":"SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models","created":"2024-06-04","cited_by_count":23,"area":"diffusion"},{"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":"2411.11925","title":"Continuous Speculative Decoding for Autoregressive Image Generation","created":"2024-11-18","cited_by_count":19,"area":"inference"},{"id":"2409.20255","title":"PerCo (SD): Open Perceptual Compression","created":"2024-09-30","cited_by_count":18,"area":"diffusion"},{"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":"2506.14198","title":"AMPLIFY: Actionless Motion Priors for Robot Learning from Videos","created":"2025-06-17","cited_by_count":18,"area":"wm"},{"id":"2408.13893","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","created":"2024-08-25","cited_by_count":17,"area":"diffusion"},{"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":"2506.16349","title":"Watermarking Autoregressive Image Generation","created":"2025-06-19","cited_by_count":16,"area":"safety"},{"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":"2507.20454","title":"Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis","created":"2025-07-28","cited_by_count":15,"area":"diffusion"},{"id":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2509.16197","title":"MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer","created":"2025-09-19","cited_by_count":15,"area":"mllm"},{"id":"2511.02097","title":"A Step Toward World Models: A Survey on Robotic Manipulation","created":"2025-10-31","cited_by_count":15,"area":"wm"},{"id":"2602.04215","title":"OAT: Ordered Action Tokenization","created":"2026-02-04","cited_by_count":15,"area":null},{"id":"2410.03755","title":"Denoising with a Joint-Embedding Predictive Architecture","created":"2024-10-02","cited_by_count":14,"area":"diffusion"},{"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":"2412.06774","title":"Visual Lexicon: Rich Image Features in Language Space","created":"2024-12-09","cited_by_count":12,"area":"mllm"},{"id":"2412.14453","title":"Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation","created":"2024-12-19","cited_by_count":12,"area":"diffusion"},{"id":"2504.00999","title":"MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization","created":"2025-04-01","cited_by_count":12,"area":"inference"},{"id":"2510.24717","title":"Uniform Discrete Diffusion with Metric Path for Video Generation","created":"2025-10-28","cited_by_count":12,"area":"diffusion"}],"next_cursor":"100"}