{"list":"other","total":103,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"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":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"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":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1712.09482","title":"Robust Loss Functions under Label Noise for Deep Neural Networks","created":"2017-12-27","cited_by_count":443},{"id":"2007.00151","title":"Early-Learning Regularization Prevents Memorization of Noisy Labels","created":"2020-06-30","cited_by_count":416},{"id":"1911.00068","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","created":"2019-10-31","cited_by_count":413},{"id":"1901.04215","title":"How does Disagreement Help Generalization against Label Corruption?","created":"2019-01-14","cited_by_count":390},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2003.02752","title":"Combating noisy labels by agreement: A joint training method with co-regularization","created":"2020-03-05","cited_by_count":289},{"id":"2211.07804","title":"Diffusion Models for Medical Image Analysis: A Comprehensive Survey","created":"2022-11-14","cited_by_count":273},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266},{"id":"1909.11764","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","created":"2019-09-25","cited_by_count":264},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"id":"2306.03083","title":"MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion","created":"2023-06-05","cited_by_count":213},{"id":"1906.00189","title":"Are Anchor Points Really Indispensable in Label-Noise Learning?","created":"2019-06-01","cited_by_count":208},{"id":"2211.13752","title":"Sketch-Guided Text-to-Image Diffusion Models","created":"2022-11-24","cited_by_count":180},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2310.20707","title":"What's In My Big Data?","created":"2023-10-31","cited_by_count":129},{"id":"2103.09396","title":"Pros and Cons of GAN Evaluation Measures: New Developments","created":"2021-03-17","cited_by_count":123},{"id":"2011.04406","title":"A Survey of Label-noise Representation Learning: Past, Present and Future","created":"2020-11-09","cited_by_count":122},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"1912.05170","title":"Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey","created":"2019-12-11","cited_by_count":101},{"id":"2310.05914","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","created":"2023-10-09","cited_by_count":100},{"id":"2102.02400","title":"Provably End-to-end Label-Noise Learning without Anchor Points","created":"2021-02-04","cited_by_count":97},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83},{"id":"2310.07771","title":"DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model","created":"2023-10-11","cited_by_count":75},{"id":"2403.05121","title":"CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion","created":"2024-03-08","cited_by_count":72},{"id":"2201.11706","title":"A Systematic Study of Bias Amplification","created":"2022-01-27","cited_by_count":65},{"id":"2102.02414","title":"Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization","created":"2021-02-04","cited_by_count":62},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61},{"id":"2010.09891","title":"Robust Optimization as Data Augmentation for Large-scale Graphs","created":"2020-10-19","cited_by_count":58},{"id":"2211.10682","title":"DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization","created":"2022-11-19","cited_by_count":45},{"id":"2202.12024","title":"NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better","created":"2022-02-24","cited_by_count":43},{"id":"2212.04055","title":"Mitigating Memorization of Noisy Labels by Clipping the Model Prediction","created":"2022-12-08","cited_by_count":40},{"id":"2105.13001","title":"Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network","created":"2021-05-27","cited_by_count":30},{"id":"2405.05538","title":"A Survey on Personalized Content Synthesis with Diffusion Models","created":"2024-05-09","cited_by_count":29},{"id":"1811.03205","title":"Robustness of Conditional GANs to Noisy Labels","created":"2018-11-08","cited_by_count":27},{"id":"2302.05496","title":"MaskSketch: Unpaired Structure-guided Masked Image Generation","created":"2023-02-10","cited_by_count":27},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27},{"id":"2302.11797","title":"Region-Aware Diffusion for Zero-shot Text-driven Image Editing","created":"2023-02-23","cited_by_count":25},{"id":"1811.11165","title":"Label-Noise Robust Generative Adversarial Networks","created":"2018-11-27","cited_by_count":22},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18},{"id":"2304.10127","title":"Learning Sample Difficulty from Pre-trained Models for Reliable Prediction","created":"2023-04-20","cited_by_count":15},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15},{"id":"2306.08013","title":"TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models","created":"2023-06-13","cited_by_count":14},{"id":"2003.07849","title":"Blur, Noise, and Compression Robust Generative Adversarial Networks","created":"2020-03-17","cited_by_count":9},{"id":"2305.12715","title":"Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations","created":"2023-05-22","cited_by_count":9},{"id":"2403.10853","title":"GenOL: Generating Diverse Examples for Name-only Online Learning","created":"2024-03-16","cited_by_count":9},{"id":"2403.06869","title":"Impact of Noisy Supervision in Foundation Model Learning","created":"2024-03-11","cited_by_count":8},{"id":"2310.00900","title":"uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models","created":"2023-10-02","cited_by_count":7},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7},{"id":"2312.01523","title":"SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise","created":"2023-12-03","cited_by_count":4}],"next_cursor":"100"}