{"list":"other","total":71,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"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":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"2203.02923","title":"GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation","created":"2022-03-06","cited_by_count":516},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2210.01776","title":"DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking","created":"2022-10-04","cited_by_count":313},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"2006.08656","title":"Multiscale Deep Equilibrium Models","created":"2020-06-15","cited_by_count":151},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"id":"2204.09934","title":"FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis","created":"2022-04-21","cited_by_count":136},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120},{"id":"2006.08591","title":"Monotone operator equilibrium networks","created":"2020-06-15","cited_by_count":100},{"id":"2209.11178","title":"Poisson Flow Generative Models","created":"2022-09-22","cited_by_count":95},{"id":"1908.03835","title":"AutoGAN: Neural Architecture Search for Generative Adversarial Networks","created":"2019-08-11","cited_by_count":94},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77},{"id":"2111.05177","title":"On Training Implicit Models","created":"2021-11-09","cited_by_count":75},{"id":"2106.14342","title":"Stabilizing Equilibrium Models by Jacobian Regularization","created":"2021-06-28","cited_by_count":72},{"id":"2204.08442","title":"Deep Equilibrium Optical Flow Estimation","created":"2022-04-18","cited_by_count":64},{"id":"2010.01732","title":"Lipschitz Bounded Equilibrium Networks","created":"2020-10-05","cited_by_count":49},{"id":"2203.14206","title":"Denoising Likelihood Score Matching for Conditional Score-based Data Generation","created":"2022-03-27","cited_by_count":46},{"id":"2211.09961","title":"Path Independent Equilibrium Models Can Better Exploit Test-Time Computation","created":"2022-11-18","cited_by_count":38},{"id":"2103.09527","title":"Implicit Normalizing Flows","created":"2021-03-17","cited_by_count":28},{"id":"2304.00600","title":"Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models","created":"2023-04-02","cited_by_count":27},{"id":"2012.13563","title":"Implicit Feature Pyramid Network for Object Detection","created":"2020-12-25","cited_by_count":15},{"id":"2111.13236","title":"Joint inference and input optimization in equilibrium networks","created":"2021-11-25","cited_by_count":15},{"id":"2308.09564","title":"Deep Equilibrium Object Detection","created":"2023-08-18","cited_by_count":10},{"id":"2211.05943","title":"Deep equilibrium models as estimators for continuous latent variables","created":"2022-11-11","cited_by_count":4}],"next_cursor":null}