{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310},{"id":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304},{"id":"1804.02958","title":"Generative Adversarial Networks for Extreme Learned Image Compression","created":"2018-04-09","cited_by_count":219},{"id":"2306.04675","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","created":"2023-06-07","cited_by_count":205},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112},{"id":"2310.10325","title":"Towards image compression with perfect realism at ultra-low bitrates","created":"2023-10-16","cited_by_count":103},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94},{"id":"2206.08889","title":"Lossy Compression with Gaussian Diffusion","created":"2022-06-17","cited_by_count":90},{"id":"2404.18820","title":"Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior","created":"2024-04-29","cited_by_count":60},{"id":"2305.18231","title":"High-Fidelity Image Compression with Score-based Generative Models","created":"2023-05-26","cited_by_count":54},{"id":"2404.08580","title":"Lossy Image Compression with Foundation Diffusion Models","created":"2024-04-12","cited_by_count":36},{"id":"2506.21977","title":"StableCodec: Taming One-Step Diffusion for Extreme Image Compression","created":"2025-06-27","cited_by_count":33},{"id":"2307.08265","title":"Extreme Image Compression using Fine-tuned VQGANs","created":"2023-07-17","cited_by_count":29},{"id":"2505.16091","title":"OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates","created":"2025-05-22","cited_by_count":26},{"id":"2505.16687","title":"One-Step Diffusion-Based Image Compression with Semantic Distillation","created":"2025-05-22","cited_by_count":26},{"id":"2501.09815","title":"Lossy Compression with Pretrained Diffusion Models","created":"2025-01-16","cited_by_count":25},{"id":"2410.02640","title":"RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion","created":"2024-10-03","cited_by_count":23},{"id":"2512.20194","title":"Generative Latent Coding for Ultra-Low Bitrate Image Compression","created":"2025-12-23","cited_by_count":23},{"id":"2503.01428","title":"DLF: Extreme Image Compression with Dual-generative Latent Fusion","created":"2025-03-03","cited_by_count":21},{"id":"2408.08604","title":"Bi-Directional Deep Contextual Video Compression","created":"2024-08-16","cited_by_count":20},{"id":"2505.08281","title":"Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion","created":"2025-05-13","cited_by_count":20},{"id":"2409.20255","title":"PerCo (SD): Open Perceptual Compression","created":"2024-09-30","cited_by_count":18},{"id":"2403.03736","title":"Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer","created":"2024-03-06","cited_by_count":12},{"id":"2511.18706","title":"CoD: A Diffusion Foundation Model for Image Compression","created":"2025-11-24","cited_by_count":10},{"id":"2512.12229","title":"Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder","created":"2025-12-13","cited_by_count":7},{"id":"2604.12525","title":"CoD-Lite: Real-Time Diffusion-Based Generative Image Compression","created":"2026-04-14","cited_by_count":7},{"id":"2603.13162","title":"DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression","created":"2026-03-13","cited_by_count":5},{"id":"2604.10546","title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","created":"2026-04-12","cited_by_count":5},{"id":"2603.15129","title":"Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors","created":"2026-03-16","cited_by_count":3},{"id":"2603.17546","title":"ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling","created":"2026-03-18","cited_by_count":3},{"id":"2509.05169","title":"Exploring Autoregressive Vision Foundation Models for Image Compression","created":"2025-09-05","cited_by_count":2},{"id":"2602.21591","title":"CADC: Content Adaptive Diffusion-Based Generative Image Compression","created":"2026-02-25","cited_by_count":2}],"next_cursor":null}