{"total":1123,"rows":[{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627,"area":null},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511,"area":null},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027,"area":null},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995,"area":null},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727,"area":null},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658,"area":null},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651,"area":null},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492,"area":null},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483,"area":null},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442,"area":null},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385,"area":null},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320,"area":null},{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311,"area":null},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304,"area":null},{"id":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304,"area":null},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288,"area":null},{"id":"2110.06197","title":"Crystal Diffusion Variational Autoencoder for Periodic Material Generation","created":"2021-10-12","cited_by_count":270,"area":null},{"id":"2206.01729","title":"Torsional Diffusion for Molecular Conformer Generation","created":"2022-06-01","cited_by_count":263,"area":null},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260,"area":null},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245,"area":null},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238,"area":null},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2211.09117","title":"MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis","created":"2022-11-16","cited_by_count":227,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2110.11291","title":"Likelihood Training of Schr\\\"odinger Bridge using Forward-Backward SDEs Theory","created":"2021-10-21","cited_by_count":219,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2406.19435","title":"A Sanity Check for AI-generated Image Detection","created":"2024-06-27","cited_by_count":189,"area":null},{"id":"2203.13777","title":"Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion","created":"2022-03-25","cited_by_count":185,"area":null},{"id":"2301.11699","title":"Image Restoration with Mean-Reverting Stochastic Differential Equations","created":"2023-01-27","cited_by_count":183,"area":null},{"id":"2302.10109","title":"NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion","created":"2023-02-20","cited_by_count":180,"area":null},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177,"area":null},{"id":"2303.03543","title":"3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction","created":"2023-03-06","cited_by_count":177,"area":null},{"id":"2206.13397","title":"Generative Modelling With Inverse Heat Dissipation","created":"2022-06-21","cited_by_count":167,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154,"area":null},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147,"area":null},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136,"area":null},{"id":"2209.08725","title":"Neural Wavelet-domain Diffusion for 3D Shape Generation","created":"2022-09-19","cited_by_count":132,"area":null},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2209.09002","title":"MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation","created":"2022-09-19","cited_by_count":125,"area":null},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124,"area":null},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123,"area":null},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2403.05897","title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","created":"2024-03-09","cited_by_count":116,"area":null},{"id":"2403.08733","title":"GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing","created":"2024-03-13","cited_by_count":115,"area":null},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114,"area":null},{"id":"2104.09425","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","created":"2021-04-19","cited_by_count":113,"area":null},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2307.01198","title":"Improved sampling via learned diffusions","created":"2023-07-03","cited_by_count":104,"area":null},{"id":"2112.06749","title":"Step-unrolled Denoising Autoencoders for Text Generation","created":"2021-12-13","cited_by_count":102,"area":null},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102,"area":null},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101,"area":null},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100,"area":null},{"id":"2310.03725","title":"Stochastic interpolants with data-dependent couplings","created":"2023-10-05","cited_by_count":100,"area":null},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99,"area":null},{"id":"2312.03701","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","created":"2023-12-06","cited_by_count":98,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"area":null},{"id":"2306.10574","title":"Score-based Data Assimilation","created":"2023-06-18","cited_by_count":96,"area":null},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93,"area":null},{"id":"2412.06329","title":"Normalizing Flows are Capable Generative Models","created":"2024-12-09","cited_by_count":91,"area":null},{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90,"area":null},{"id":"2304.09218","title":"Generative models improve fairness of medical classifiers under distribution shifts","created":"2023-04-18","cited_by_count":90,"area":null},{"id":"2412.08821","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","created":"2024-12-11","cited_by_count":89,"area":null},{"id":"2502.09509","title":"EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling","created":"2025-02-13","cited_by_count":89,"area":null},{"id":"2202.10166","title":"Diffusion Causal Models for Counterfactual Estimation","created":"2022-02-21","cited_by_count":87,"area":null},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2512.04678","title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","created":"2025-12-04","cited_by_count":86,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2303.17606","title":"AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control","created":"2023-03-30","cited_by_count":84,"area":null},{"id":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83,"area":null},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83,"area":null},{"id":"2303.05021","title":"DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation","created":"2023-03-09","cited_by_count":82,"area":null},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82,"area":null},{"id":"2305.12529","title":"DreamWaltz: Make a Scene with Complex 3D Animatable Avatars","created":"2023-05-21","cited_by_count":82,"area":null},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82,"area":null},{"id":"2302.03665","title":"HumanMAC: Masked Motion Completion for Human Motion Prediction","created":"2023-02-07","cited_by_count":81,"area":null},{"id":"2311.00213","title":"Consistent Video-to-Video Transfer Using Synthetic Dataset","created":"2023-11-01","cited_by_count":81,"area":null},{"id":"2304.00917","title":"Diffusion Bridge Mixture Transports, Schr\\\"odinger Bridge Problems and Generative Modeling","created":"2023-04-03","cited_by_count":80,"area":null},{"id":"2402.15509","title":"Seamless Human Motion Composition with Blended Positional Encodings","created":"2024-02-23","cited_by_count":80,"area":null},{"id":"2312.06704","title":"SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction","created":"2023-12-10","cited_by_count":77,"area":null},{"id":"2304.10532","title":"Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs","created":"2023-04-20","cited_by_count":76,"area":null},{"id":"2304.06711","title":"DiffusionRig: Learning Personalized Priors for Facial Appearance Editing","created":"2023-04-13","cited_by_count":75,"area":null},{"id":"2209.15408","title":"Equivariant Energy-Guided SDE for Inverse Molecular Design","created":"2022-09-30","cited_by_count":73,"area":null},{"id":"2402.03992","title":"Space Group Constrained Crystal Generation","created":"2024-02-06","cited_by_count":73,"area":null},{"id":"2204.07156","title":"Any-resolution Training for High-resolution Image Synthesis","created":"2022-04-14","cited_by_count":72,"area":null},{"id":"2207.03442","title":"Back to the Source: Diffusion-Driven Test-Time Adaptation","created":"2022-07-07","cited_by_count":71,"area":null},{"id":"2301.03362","title":"Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --","created":"2023-01-09","cited_by_count":71,"area":null},{"id":"2307.15208","title":"Generative AI for Medical Imaging: extending the MONAI Framework","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2303.07945","title":"Edit-A-Video: Single Video Editing with Object-Aware Consistency","created":"2023-03-14","cited_by_count":67,"area":null},{"id":"2112.09164","title":"High Fidelity Visualization of What Your Self-Supervised Representation Knows About","created":"2021-12-16","cited_by_count":66,"area":null},{"id":"2304.13023","title":"Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images","created":"2023-04-25","cited_by_count":66,"area":null},{"id":"2305.07508","title":"MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation","created":"2023-05-11","cited_by_count":65,"area":null},{"id":"2305.15560","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","created":"2023-05-24","cited_by_count":65,"area":null}],"next_cursor":"100"}