{"list":"other","total":70,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2406.07209","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","created":"2024-06-11","cited_by_count":144},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"2306.06101","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","created":"2023-06-09","cited_by_count":133},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"2410.03456","title":"Dynamic Diffusion Transformer","created":"2024-10-04","cited_by_count":62},{"id":"2305.02567","title":"LayoutDM: Transformer-based Diffusion Model for Layout Generation","created":"2023-05-04","cited_by_count":57},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50},{"id":"2312.04410","title":"Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models","created":"2023-12-07","cited_by_count":49},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44},{"id":"2208.08037","title":"LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction","created":"2022-08-17","cited_by_count":43},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41},{"id":"2303.05049","title":"Unifying Layout Generation with a Decoupled Diffusion Model","created":"2023-03-09","cited_by_count":41},{"id":"2406.02884","title":"PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM","created":"2024-06-05","cited_by_count":41},{"id":"2404.14368","title":"Graphic Design with Large Multimodal Model","created":"2024-04-22","cited_by_count":40},{"id":"2304.04237","title":"Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention","created":"2023-04-09","cited_by_count":38},{"id":"2404.02790","title":"MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation","created":"2024-04-03","cited_by_count":38},{"id":"2307.09781","title":"Text2Layer: Layered Image Generation using Latent Diffusion Model","created":"2023-07-19","cited_by_count":37},{"id":"2406.08232","title":"OpenCOLE: Towards Reproducible Automatic Graphic Design Generation","created":"2024-06-12","cited_by_count":37},{"id":"2303.00262","title":"Collage Diffusion","created":"2023-03-01","cited_by_count":33},{"id":"2306.11248","title":"Dynamic Perceiver for Efficient Visual Recognition","created":"2023-06-20","cited_by_count":33},{"id":"2410.07171","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","created":"2024-10-09","cited_by_count":33},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31},{"id":"2304.03119","title":"Zero-shot Generative Model Adaptation via Image-specific Prompt Learning","created":"2023-04-06","cited_by_count":27},{"id":"2308.15949","title":"Latency-aware Unified Dynamic Networks for Efficient Image Recognition","created":"2023-08-30","cited_by_count":26},{"id":"2403.11929","title":"LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model","created":"2024-03-18","cited_by_count":26},{"id":"2210.06223","title":"Latency-aware Spatial-wise Dynamic Networks","created":"2022-10-12","cited_by_count":25},{"id":"2301.11529","title":"PLay: Parametrically Conditioned Layout Generation using Latent Diffusion","created":"2023-01-27","cited_by_count":24},{"id":"2408.05710","title":"Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators","created":"2024-08-11","cited_by_count":24},{"id":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","cited_by_count":23},{"id":"2309.01430","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","created":"2023-09-04","cited_by_count":21},{"id":"2403.18187","title":"LayoutFlow: Flow Matching for Layout Generation","created":"2024-03-27","cited_by_count":21},{"id":"2403.09093","title":"Desigen: A Pipeline for Controllable Design Template Generation","created":"2024-03-14","cited_by_count":19},{"id":"1904.00761","title":"Neural Speed Reading with Structural-Jump-LSTM","created":"2019-03-20","cited_by_count":17},{"id":"2309.00399","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","created":"2023-09-01","cited_by_count":17},{"id":"2409.19051","title":"Multimodal Markup Document Models for Graphic Design Completion","created":"2024-09-27","cited_by_count":16},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14},{"id":"2411.10913","title":"Generating Compositional Scenes via Text-to-image RGBA Instance Generation","created":"2024-11-16","cited_by_count":14},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13},{"id":"2403.11127","title":"GRA: Detecting Oriented Objects through Group-wise Rotating and Attention","created":"2024-03-17","cited_by_count":13},{"id":"2409.00342","title":"AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation","created":"2024-08-31","cited_by_count":13},{"id":"2412.11228","title":"Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition","created":"2024-12-15","cited_by_count":9},{"id":"2410.12844","title":"TextLap: Customizing Language Models for Text-to-Layout Planning","created":"2024-10-09","cited_by_count":8},{"id":"2411.06959","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","created":"2024-11-11","cited_by_count":8},{"id":"2407.20080","title":"UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation","created":"2024-07-29","cited_by_count":6},{"id":"2412.05003","title":"SLayR: Scene Layout Generation with Rectified Flow","created":"2024-12-06","cited_by_count":2}],"next_cursor":null}