{"list":"other","total":162,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"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":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2009.00713","title":"WaveGrad: Estimating Gradients for Waveform Generation","created":"2020-09-02","cited_by_count":622},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2203.02923","title":"GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation","created":"2022-03-06","cited_by_count":516},{"id":"2305.07015","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","created":"2023-05-11","cited_by_count":489},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"1905.07088","title":"Sliced Score Matching: A Scalable Approach to Density and Score Estimation","created":"2019-05-17","cited_by_count":384},{"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":"2112.05146","title":"Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction","created":"2021-12-09","cited_by_count":307},{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2303.14420","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","created":"2023-03-25","cited_by_count":287},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"2202.02514","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","created":"2022-02-05","cited_by_count":283},{"id":"2101.03288","title":"How to Train Your Energy-Based Models","created":"2021-01-09","cited_by_count":274},{"id":"2211.07804","title":"Diffusion Models for Medical Image Analysis: A Comprehensive Survey","created":"2022-11-14","cited_by_count":273},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263},{"id":"1905.07121","title":"Simple Black-box Adversarial Attacks","created":"2019-05-17","cited_by_count":251},{"id":"2305.13655","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","created":"2023-05-23","cited_by_count":243},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"2303.11408","title":"Stable Bias: Analyzing Societal Representations in Diffusion Models","created":"2023-03-20","cited_by_count":226},{"id":"2302.02277","title":"SE(3) diffusion model with application to protein backbone generation","created":"2023-02-05","cited_by_count":219},{"id":"2211.15089","title":"Continuous diffusion for categorical data","created":"2022-11-28","cited_by_count":214},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2212.11972","title":"Scalable Adaptive Computation for Iterative Generation","created":"2022-12-22","cited_by_count":195},{"id":"2303.03543","title":"3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction","created":"2023-03-06","cited_by_count":177},{"id":"2305.13873","title":"Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models","created":"2023-05-23","cited_by_count":175},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173},{"id":"2206.13397","title":"Generative Modelling With Inverse Heat Dissipation","created":"2022-06-21","cited_by_count":167},{"id":"2103.16091","title":"Symbolic Music Generation with Diffusion Models","created":"2021-03-30","cited_by_count":154},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"2302.05737","title":"A Reparameterized Discrete Diffusion Model for Text Generation","created":"2023-02-11","cited_by_count":152},{"id":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2305.09515","title":"AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation","created":"2023-05-16","cited_by_count":118},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112},{"id":"2305.19256","title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data","created":"2023-05-30","cited_by_count":111},{"id":"1705.02498","title":"A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions","created":"2017-05-06","cited_by_count":108},{"id":"2305.13311","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","created":"2023-05-22","cited_by_count":103},{"id":"2112.03530","title":"A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion","created":"2021-12-07","cited_by_count":100},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100},{"id":"1903.01608","title":"Theoretical guarantees for sampling and inference in generative models with latent diffusions","created":"2019-03-05","cited_by_count":97},{"id":"2305.08192","title":"Diffusion Models for Imperceptible and Transferable Adversarial Attack","created":"2023-05-14","cited_by_count":94},{"id":"2305.04175","title":"Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning","created":"2023-05-07","cited_by_count":92},{"id":"2302.02591","title":"Generative Diffusion Models on Graphs: Methods and Applications","created":"2023-02-06","cited_by_count":81},{"id":"2106.06406","title":"PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior","created":"2021-06-11","cited_by_count":80},{"id":"2305.10699","title":"Dirichlet Diffusion Score Model for Biological Sequence Generation","created":"2023-05-18","cited_by_count":75},{"id":"2209.15408","title":"Equivariant Energy-Guided SDE for Inverse Molecular Design","created":"2022-09-30","cited_by_count":73},{"id":"2305.00624","title":"Diffusion Models for Time Series Applications: A Survey","created":"2023-05-01","cited_by_count":72},{"id":"2302.13153","title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance","created":"2023-02-25","cited_by_count":69},{"id":"2303.13336","title":"A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI","created":"2023-03-23","cited_by_count":68},{"id":"2212.00842","title":"3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models","created":"2022-12-01","cited_by_count":67},{"id":"2305.16494","title":"Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability","created":"2023-05-25","cited_by_count":66},{"id":"2303.09051","title":"Robust Evaluation of Diffusion-Based Adversarial Purification","created":"2023-03-16","cited_by_count":65},{"id":"2305.07508","title":"MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation","created":"2023-05-11","cited_by_count":65},{"id":"2111.04726","title":"Estimating High Order Gradients of the Data Distribution by Denoising","created":"2021-11-08","cited_by_count":64}],"next_cursor":"100"}