{"list":"other","total":54,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"1901.06767","title":"LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators","created":"2019-01-21","cited_by_count":131},{"id":"2006.14615","title":"LayoutTransformer: Layout Generation and Completion with Self-attention","created":"2020-06-25","cited_by_count":123},{"id":"1907.10719","title":"LayoutVAE: Stochastic Scene Layout Generation From a Label Set","created":"2019-07-24","cited_by_count":119},{"id":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95},{"id":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"2302.13153","title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance","created":"2023-02-25","cited_by_count":69},{"id":"1811.09845","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","created":"2018-11-24","cited_by_count":61},{"id":"2007.11744","title":"End-to-End Optimization of Scene Layout","created":"2020-07-23","cited_by_count":52},{"id":"2304.03869","title":"Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis","created":"2023-04-07","cited_by_count":51},{"id":"2009.09566","title":"SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning","created":"2020-09-21","cited_by_count":32},{"id":"2203.02104","title":"Interactive Image Synthesis with Panoptic Layout Generation","created":"2022-03-04","cited_by_count":17},{"id":"2303.03565","title":"CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding","created":"2023-03-07","cited_by_count":16}],"next_cursor":null}