{"total":22,"rows":[{"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":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55,"area":null},{"id":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40,"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":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23,"area":null},{"id":"2306.00238","title":"Bytes Are All You Need: Transformers Operating Directly On File Bytes","created":"2023-05-31","cited_by_count":18,"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":"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":"2412.10443","title":"SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization","created":"2024-12-11","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":"2405.14206","title":"LG-VQ: Language-Guided Codebook Learning","created":"2024-05-23","cited_by_count":10,"area":null},{"id":"2501.04975","title":"V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer","created":"2025-01-09","cited_by_count":9,"area":null},{"id":"2403.16394","title":"Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation","created":"2024-03-25","cited_by_count":8,"area":null},{"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":"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":"2307.00028","title":"Seeing in Words: Learning to Classify through Language Bottlenecks","created":"2023-06-29","cited_by_count":2,"area":null},{"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":"2603.01074","title":"Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation","created":"2026-03-01","cited_by_count":0,"area":null},{"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}