{"total":55,"rows":[{"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":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366,"area":"diffusion"},{"id":"2507.01467","title":"Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think","created":"2025-07-02","cited_by_count":102,"area":"diffusion"},{"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":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94,"area":"diffusion"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2406.11837","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","created":"2024-06-17","cited_by_count":68,"area":null},{"id":"2406.09750","title":"ControlVAR: Exploring Controllable Visual Autoregressive Modeling","created":"2024-06-14","cited_by_count":58,"area":"diffusion"},{"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":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2403.15132","title":"Transfer CLIP for Generalizable Image Denoising","created":"2024-03-22","cited_by_count":29,"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":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23,"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":"2403.10071","title":"Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2412.03085","title":"Mimir: Improving Video Diffusion Models for Precise Text Understanding","created":"2024-12-04","cited_by_count":16,"area":"diffusion"},{"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":"2311.00618","title":"De-Diffusion Makes Text a Strong Cross-Modal Interface","created":"2023-11-01","cited_by_count":14,"area":"diffusion"},{"id":"2403.09072","title":"UniCode: Learning a Unified Codebook for Multimodal Large Language Models","created":"2024-03-14","cited_by_count":14,"area":"mllm"},{"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":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"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":"2412.06774","title":"Visual Lexicon: Rich Image Features in Language Space","created":"2024-12-09","cited_by_count":12,"area":"mllm"},{"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":"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":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12,"area":null},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","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":"2405.14206","title":"LG-VQ: Language-Guided Codebook Learning","created":"2024-05-23","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":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2311.04589","title":"TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models","created":"2023-11-08","cited_by_count":7,"area":"mllm"},{"id":"2403.06128","title":"Low-dose CT Denoising with Language-engaged Dual-space Alignment","created":"2024-03-10","cited_by_count":7,"area":null},{"id":"2406.15504","title":"Multi-View Empowered Structural Graph Wordification for Language Models","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2311.16201","title":"Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2503.07493","title":"V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2601.03955","title":"ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation","created":"2026-01-07","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":"2502.14888","title":"Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models","created":"2025-02-16","cited_by_count":4,"area":"mllm"},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2507.07104","title":"Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models","created":"2025-07-09","cited_by_count":4,"area":"mllm"},{"id":"2402.02636","title":"Can Large Language Models Learn Independent Causal Mechanisms?","created":"2024-02-04","cited_by_count":3,"area":"lr"},{"id":"2502.17863","title":"A Survey: Spatiotemporal Consistency in Video Generation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2507.06140","title":"LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2507.06507","title":"GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models","created":"2025-07-09","cited_by_count":3,"area":"lr"},{"id":"2410.20109","title":"GiVE: Guiding Visual Encoder to Perceive Overlooked Information","created":"2024-10-26","cited_by_count":2,"area":"mllm"},{"id":"2405.16728","title":"Towards Multi-Task Multi-Modal Models: A Video Generative Perspective","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2412.14145","title":"Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2503.00427","title":"Language Model Mapping in Multimodal Music Learning: A Grand Challenge Proposal","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2605.30904","title":"MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging","created":"2026-05-29","cited_by_count":0,"area":"inference"},{"id":"2610.16552","title":"Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}