{"list":"other","total":51,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"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":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"2504.05741","title":"DDT: Decoupled Diffusion Transformer","created":"2025-04-08","cited_by_count":109},{"id":"2310.10325","title":"Towards image compression with perfect realism at ultra-low bitrates","created":"2023-10-16","cited_by_count":103},{"id":"2502.03444","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","created":"2025-02-05","cited_by_count":96},{"id":"2206.08889","title":"Lossy Compression with Gaussian Diffusion","created":"2022-06-17","cited_by_count":90},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84},{"id":"2307.01944","title":"Text + Sketch: Image Compression at Ultra Low Rates","created":"2023-07-04","cited_by_count":67},{"id":"2404.18820","title":"Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior","created":"2024-04-29","cited_by_count":60},{"id":"2511.19365","title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","created":"2025-11-24","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":"2604.28190","title":"Representation Fr\\'echet Loss for Visual Generation","created":"2026-04-30","cited_by_count":37},{"id":"2301.05489","title":"A Residual Diffusion Model for High Perceptual Quality Codec Augmentation","created":"2023-01-13","cited_by_count":35},{"id":"2506.21977","title":"StableCodec: Taming One-Step Diffusion for Extreme Image Compression","created":"2025-06-27","cited_by_count":33},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31},{"id":"2512.07829","title":"One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation","created":"2025-12-08","cited_by_count":28},{"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":"2502.00359","title":"Exploring Representation-Aligned Latent Space for Better Generation","created":"2025-02-01","cited_by_count":22},{"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":"2512.24176","title":"Guiding a Diffusion Transformer with the Internal Dynamics of Itself","created":"2025-12-30","cited_by_count":16},{"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}],"next_cursor":null}