{"total":191,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777,"area":null},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651,"area":null},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457,"area":null},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400,"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":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"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":"2409.04410","title":"Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation","created":"2024-09-06","cited_by_count":155,"area":null},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2411.00776","title":"Randomized Autoregressive Visual Generation","created":"2024-11-01","cited_by_count":127,"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":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105,"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":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99,"area":null},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92,"area":null},{"id":"2307.06940","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","created":"2023-07-13","cited_by_count":90,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78,"area":null},{"id":"2312.04551","title":"Free3D: Consistent Novel View Synthesis without 3D Representation","created":"2023-12-07","cited_by_count":72,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69,"area":null},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60,"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":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2501.07730","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","created":"2025-01-13","cited_by_count":50,"area":null},{"id":"2503.10076","title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation","created":"2025-03-13","cited_by_count":49,"area":null},{"id":"2402.13185","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","created":"2024-02-20","cited_by_count":48,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"area":null},{"id":"2410.21264","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","created":"2024-10-28","cited_by_count":46,"area":null},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","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":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2411.08380","title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","created":"2024-11-13","cited_by_count":41,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2403.19438","title":"SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control","created":"2024-03-28","cited_by_count":32,"area":null},{"id":"2503.17076","title":"Halton Scheduler For Masked Generative Image Transformer","created":"2025-03-21","cited_by_count":32,"area":null},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2512.09299","title":"VABench: A Comprehensive Benchmark for Audio-Video Generation","created":"2025-12-10","cited_by_count":30,"area":null},{"id":"2403.13745","title":"Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation","created":"2024-03-20","cited_by_count":29,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2503.10696","title":"Neighboring Autoregressive Modeling for Efficient Visual Generation","created":"2025-03-12","cited_by_count":29,"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":"2506.18899","title":"FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation","created":"2025-06-23","cited_by_count":28,"area":null},{"id":"2402.18115","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2503.05305","title":"Frequency Autoregressive Image Generation with Continuous Tokens","created":"2025-03-07","cited_by_count":27,"area":null},{"id":"2603.12513","title":"MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens","created":"2026-03-12","cited_by_count":27,"area":null},{"id":"2412.15321","title":"Next Patch Prediction for Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":26,"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":"2310.14400","title":"A Pytorch Reproduction of Masked Generative Image Transformer","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2405.04682","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","created":"2024-05-07","cited_by_count":25,"area":null},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23,"area":null},{"id":"2502.20313","title":"FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction","created":"2025-02-27","cited_by_count":23,"area":null},{"id":"2505.23742","title":"MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2404.15955","title":"Beyond Deepfake Images: Detecting AI-Generated Videos","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2410.10511","title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2505.03351","title":"GUAVA: Generalizable Upper Body 3D Gaussian Avatar","created":"2025-05-06","cited_by_count":22,"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":"2306.05957","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","created":"2023-06-09","cited_by_count":19,"area":null},{"id":"2501.15420","title":"Visual Generation Without Guidance","created":"2025-01-26","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":"2410.04081","title":"Epsilon-VAE: Denoising as Visual Decoding","created":"2024-10-05","cited_by_count":16,"area":null},{"id":"2410.23159","title":"Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting","created":"2024-10-30","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":"2506.14168","title":"VideoMAR: Autoregressive Video Generatio with Continuous Tokens","created":"2025-06-17","cited_by_count":16,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"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":"2501.01425","title":"Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation","created":"2025-01-02","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2507.15897","title":"ReDi: Rectified Discrete Flow","created":"2025-07-21","cited_by_count":14,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2506.07865","title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","created":"2025-06-09","cited_by_count":13,"area":null},{"id":"2507.04947","title":"DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer","created":"2025-07-07","cited_by_count":13,"area":null},{"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":"2412.10443","title":"SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization","created":"2024-12-11","cited_by_count":12,"area":null},{"id":"2502.11234","title":"MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation","created":"2025-02-16","cited_by_count":12,"area":null},{"id":"2503.00948","title":"Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think","created":"2025-03-02","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":"2507.02358","title":"Hita: Holistic Tokenizer for Autoregressive Image Generation","created":"2025-07-03","cited_by_count":11,"area":null},{"id":"2302.08641","title":"Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey","created":"2023-02-17","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":"2411.19537","title":"Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook","created":"2024-11-29","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":"2511.19320","title":"SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation","created":"2025-11-24","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":"2407.07356","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators","created":"2024-07-10","cited_by_count":9,"area":null},{"id":"2410.03143","title":"ECHOPulse: ECG controlled echocardio-grams video generation","created":"2024-10-04","cited_by_count":9,"area":null},{"id":"2504.08959","title":"MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer","created":"2025-04-11","cited_by_count":9,"area":null}],"next_cursor":"100"}