{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"2210.10960","title":"Diffusion Models already have a Semantic Latent Space","created":"2022-10-20","cited_by_count":328},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312},{"id":"2204.00227","title":"Perception Prioritized Training of Diffusion Models","created":"2022-04-01","cited_by_count":303},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205},{"id":"2305.10120","title":"Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models","created":"2023-05-17","cited_by_count":177},{"id":"2108.00946","title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","created":"2021-08-02","cited_by_count":164},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","cited_by_count":124},{"id":"2308.01508","title":"Circumventing Concept Erasure Methods For Text-to-Image Generative Models","created":"2023-08-03","cited_by_count":85},{"id":"2305.19693","title":"Spontaneous Symmetry Breaking in Generative Diffusion Models","created":"2023-05-31","cited_by_count":80},{"id":"2311.17216","title":"Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation","created":"2023-11-28","cited_by_count":69},{"id":"2402.05375","title":"Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models","created":"2024-02-08","cited_by_count":63},{"id":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50},{"id":"2203.16931","title":"Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond","created":"2022-03-31","cited_by_count":48},{"id":"2309.04430","title":"Create Your World: Lifelong Text-to-Image Diffusion","created":"2023-09-08","cited_by_count":46},{"id":"2410.17594","title":"How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?","created":"2024-10-23","cited_by_count":33},{"id":"2210.17004","title":"Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution","created":"2022-10-31","cited_by_count":28},{"id":"2211.11337","title":"DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter","created":"2022-11-21","cited_by_count":24},{"id":"2212.09254","title":"TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization","created":"2022-12-19","cited_by_count":21},{"id":"2301.01413","title":"Attribute-Centric Compositional Text-to-Image Generation","created":"2023-01-04","cited_by_count":19},{"id":"2309.04399","title":"MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask","created":"2023-09-08","cited_by_count":17},{"id":"2406.00773","title":"Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting","created":"2024-06-02","cited_by_count":12},{"id":"2407.15661","title":"DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving","created":"2024-07-22","cited_by_count":11},{"id":"2409.05427","title":"TextToucher: Fine-Grained Text-to-Touch Generation","created":"2024-09-09","cited_by_count":11},{"id":"2301.12247","title":"SEGA: Instructing Text-to-Image Models using Semantic Guidance","created":"2023-01-28","cited_by_count":4}],"next_cursor":null}