{"list":"other","total":115,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"1512.09300","title":"Autoencoding beyond pixels using a learned similarity metric","created":"2015-12-31","cited_by_count":407},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","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":"1907.02544","title":"Large Scale Adversarial Representation Learning","created":"2019-07-04","cited_by_count":239},{"id":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"1605.09304","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","created":"2016-05-30","cited_by_count":181},{"id":"2305.18274","title":"Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors","created":"2023-05-29","cited_by_count":160},{"id":"2211.06956","title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","created":"2022-11-13","cited_by_count":144},{"id":"2208.12266","title":"Decoding speech perception from non-invasive brain recordings","created":"2022-08-25","cited_by_count":130},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122},{"id":"2109.05070","title":"Instance-Conditioned GAN","created":"2021-09-10","cited_by_count":121},{"id":"1510.06479","title":"Generic decoding of seen and imagined objects using hierarchical visual features","created":"2015-10-22","cited_by_count":120},{"id":"2303.05334","title":"Natural scene reconstruction from fMRI signals using generative latent diffusion","created":"2023-03-09","cited_by_count":97},{"id":"1909.11646","title":"High Fidelity Speech Synthesis with Adversarial Networks","created":"2019-09-25","cited_by_count":92},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87},{"id":"2210.01769","title":"Mind Reader: Reconstructing complex images from brain activities","created":"2022-09-30","cited_by_count":85},{"id":"1805.06427","title":"MOABB: Trustworthy algorithm benchmarking for BCIs","created":"2018-05-16","cited_by_count":82},{"id":"1609.00344","title":"Deep Learning Human Mind for Automated Visual Classification","created":"2016-09-01","cited_by_count":77},{"id":"2305.11675","title":"Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity","created":"2023-05-19","cited_by_count":71},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69},{"id":"1907.02431","title":"From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI","created":"2019-07-03","cited_by_count":67},{"id":"2310.19812","title":"Brain decoding: toward real-time reconstruction of visual perception","created":"2023-10-18","cited_by_count":66},{"id":"1809.01281","title":"BOLD5000: A public fMRI dataset of 5000 images","created":"2018-09-05","cited_by_count":63},{"id":"2210.06756","title":"Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features","created":"2022-10-13","cited_by_count":63},{"id":"1608.03425","title":"Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision","created":"2016-08-11","cited_by_count":60},{"id":"2306.16934","title":"DreamDiffusion: Generating High-Quality Images from Brain EEG Signals","created":"2023-06-29","cited_by_count":56},{"id":"2202.12692","title":"Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANs","created":"2022-02-25","cited_by_count":55},{"id":"1810.10974","title":"Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features","created":"2018-10-25","cited_by_count":52},{"id":"2212.02409","title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","created":"2022-12-05","cited_by_count":49},{"id":"2308.04249","title":"MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion","created":"2023-08-08","cited_by_count":47},{"id":"2001.11761","title":"Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN","created":"2020-01-31","cited_by_count":44},{"id":"2310.02265","title":"DREAM: Visual Decoding from Reversing Human Visual System","created":"2023-10-03","cited_by_count":44},{"id":"1810.03856","title":"Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks","created":"2018-10-09","cited_by_count":43},{"id":"1804.09535","title":"Deep Convolutional AutoEncoder-based Lossy Image Compression","created":"2018-04-25","cited_by_count":42},{"id":"2308.07428","title":"UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity","created":"2023-08-14","cited_by_count":42},{"id":"2309.04509","title":"The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion","created":"2023-09-08","cited_by_count":41},{"id":"2302.12971","title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","created":"2023-02-25","cited_by_count":36},{"id":"2305.17214","title":"Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities","created":"2023-05-26","cited_by_count":36},{"id":"2309.14030","title":"DeWave: Discrete EEG Waves Encoding for Brain Dynamics to Text Translation","created":"2023-09-25","cited_by_count":36},{"id":"2305.11560","title":"Brain Captioning: Decoding human brain activity into images and text","created":"2023-05-19","cited_by_count":34},{"id":"2101.12083","title":"Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN","created":"2021-01-28","cited_by_count":32},{"id":"2305.12248","title":"Brain encoding models based on multimodal transformers can transfer across language and vision","created":"2023-05-20","cited_by_count":32}],"next_cursor":"100"}