{"list":"other","total":55,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2202.09778","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","created":"2022-02-20","cited_by_count":700},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"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":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"1803.08664","title":"Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network","created":"2018-03-23","cited_by_count":264},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"1907.05791","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","created":"2019-07-10","cited_by_count":223},{"id":"2008.05865","title":"DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis","created":"2020-08-13","cited_by_count":162},{"id":"2003.12237","title":"Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations","created":"2020-03-27","cited_by_count":133},{"id":"1911.02744","title":"PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation","created":"2019-11-07","cited_by_count":114},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100},{"id":"2106.06819","title":"D2C: Diffusion-Denoising Models for Few-shot Conditional Generation","created":"2021-06-12","cited_by_count":96},{"id":"2211.06679","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","created":"2022-11-12","cited_by_count":85},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71},{"id":"1904.01480","title":"Semantics Disentangling for Text-to-Image Generation","created":"2019-04-02","cited_by_count":61},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35},{"id":"2104.11587","title":"ESResNe(X)t-fbsp: Learning Robust Time-Frequency Transformation of Audio","created":"2021-04-23","cited_by_count":24}],"next_cursor":null}