{"total":1261,"rows":[{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511,"area":null},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995,"area":null},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658,"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":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312,"area":null},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266,"area":null},{"id":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264,"area":null},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254,"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":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250,"area":null},{"id":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","cited_by_count":248,"area":null},{"id":"2111.07677","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","created":"2021-11-15","cited_by_count":227,"area":null},{"id":"2211.14461","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","created":"2022-11-26","cited_by_count":223,"area":null},{"id":"2203.06026","title":"The Role of ImageNet Classes in Fr\\'echet Inception Distance","created":"2022-03-11","cited_by_count":213,"area":null},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208,"area":null},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2109.05923","title":"Low-Light Image Enhancement with Normalizing Flow","created":"2021-09-13","cited_by_count":185,"area":null},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2208.09481","title":"Graph neural networks for materials science and chemistry","created":"2022-08-05","cited_by_count":182,"area":null},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"area":null},{"id":"2105.09016","title":"E(n) Equivariant Normalizing Flows","created":"2021-05-19","cited_by_count":165,"area":null},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154,"area":null},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153,"area":null},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152,"area":null},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152,"area":null},{"id":"2211.00802","title":"Concrete Score Matching: Generalized Score Matching for Discrete Data","created":"2022-11-02","cited_by_count":148,"area":null},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133,"area":null},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"area":null},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126,"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":"2303.00938","title":"UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy","created":"2023-03-02","cited_by_count":124,"area":null},{"id":"2311.12397","title":"PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection","created":"2023-11-21","cited_by_count":122,"area":null},{"id":"2104.06979","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","created":"2021-04-14","cited_by_count":116,"area":null},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113,"area":null},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109,"area":null},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2206.10535","title":"EpiGRAF: Rethinking training of 3D GANs","created":"2022-06-21","cited_by_count":108,"area":null},{"id":"2108.03690","title":"Enhanced Invertible Encoding for Learned Image Compression","created":"2021-08-08","cited_by_count":105,"area":null},{"id":"2106.10410","title":"Deep Generative Learning via Schr\\\"{o}dinger Bridge","created":"2021-06-19","cited_by_count":104,"area":null},{"id":"2204.09410","title":"Generating 3D Molecules for Target Protein Binding","created":"2022-04-19","cited_by_count":104,"area":null},{"id":"2110.13040","title":"Neural Flows: Efficient Alternative to Neural ODEs","created":"2021-10-25","cited_by_count":101,"area":null},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"id":"2209.11178","title":"Poisson Flow Generative Models","created":"2022-09-22","cited_by_count":95,"area":null},{"id":"2103.15061","title":"Invertible Image Signal Processing","created":"2021-03-28","cited_by_count":94,"area":null},{"id":"2103.16173","title":"Contrastive Embedding for Generalized Zero-Shot Learning","created":"2021-03-30","cited_by_count":94,"area":null},{"id":"2104.14726","title":"MOOD: Multi-level Out-of-distribution Detection","created":"2021-04-30","cited_by_count":94,"area":null},{"id":"2104.14754","title":"Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing","created":"2021-04-30","cited_by_count":91,"area":null},{"id":"2412.06329","title":"Normalizing Flows are Capable Generative Models","created":"2024-12-09","cited_by_count":91,"area":null},{"id":"2107.06908","title":"Understanding Failures in Out-of-Distribution Detection with Deep Generative Models","created":"2021-07-14","cited_by_count":89,"area":null},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2102.00546","title":"GraphEBM: Molecular Graph Generation with Energy-Based Models","created":"2021-01-31","cited_by_count":85,"area":null},{"id":"2206.07751","title":"On the Identifiability of Nonlinear ICA: Sparsity and Beyond","created":"2022-06-15","cited_by_count":85,"area":null},{"id":"2111.09996","title":"LOLNeRF: Learn from One Look","created":"2021-11-19","cited_by_count":84,"area":null},{"id":"2112.02889","title":"Joint Learning of Localized Representations from Medical Images and Reports","created":"2021-12-06","cited_by_count":81,"area":null},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79,"area":null},{"id":"2111.02813","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","created":"2021-11-04","cited_by_count":78,"area":null},{"id":"2201.10787","title":"Variational Model Inversion Attacks","created":"2022-01-26","cited_by_count":75,"area":null},{"id":"2103.15977","title":"Flow-based Kernel Prior with Application to Blind Super-Resolution","created":"2021-03-29","cited_by_count":74,"area":null},{"id":"2303.02595","title":"PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow","created":"2023-03-05","cited_by_count":74,"area":null},{"id":"2108.05301","title":"Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling","created":"2021-08-11","cited_by_count":73,"area":null},{"id":"2207.01463","title":"Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection","created":"2022-07-04","cited_by_count":72,"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":"2203.03800","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","created":"2022-03-08","cited_by_count":70,"area":null},{"id":"2103.03433","title":"Goal-Oriented Gaze Estimation for Zero-Shot Learning","created":"2021-03-05","cited_by_count":68,"area":null},{"id":"2104.10546","title":"Invertible Denoising Network: A Light Solution for Real Noise Removal","created":"2021-04-21","cited_by_count":68,"area":null},{"id":"2109.05642","title":"On the Impact of Spurious Correlation for Out-of-distribution Detection","created":"2021-09-12","cited_by_count":68,"area":null},{"id":"2112.14038","title":"DAS-PINNs: A deep adaptive sampling method for solving high-dimensional partial differential equations","created":"2021-12-28","cited_by_count":66,"area":null},{"id":"2203.14500","title":"MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design","created":"2022-03-28","cited_by_count":66,"area":null},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2207.02862","title":"Verifying the Union of Manifolds Hypothesis for Image Data","created":"2022-07-06","cited_by_count":64,"area":null},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62,"area":null},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61,"area":null},{"id":"2212.12678","title":"Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms","created":"2022-12-24","cited_by_count":61,"area":null},{"id":"2201.12179","title":"Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks","created":"2022-01-28","cited_by_count":60,"area":null},{"id":"2211.10946","title":"Normalizing Flows for Human Pose Anomaly Detection","created":"2022-11-20","cited_by_count":60,"area":null},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59,"area":null},{"id":"2102.08248","title":"Hierarchical VAEs Know What They Don't Know","created":"2021-02-16","cited_by_count":58,"area":null},{"id":"2211.11214","title":"DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding","created":"2022-11-21","cited_by_count":58,"area":null},{"id":"2203.16529","title":"CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism","created":"2022-03-30","cited_by_count":57,"area":null},{"id":"2103.00218","title":"Countering Malicious DeepFakes: Survey, Battleground, and Horizon","created":"2021-02-27","cited_by_count":56,"area":null},{"id":"2302.12014","title":"normflows: A PyTorch Package for Normalizing Flows","created":"2023-01-26","cited_by_count":56,"area":null},{"id":"2103.10426","title":"Using latent space regression to analyze and leverage compositionality in GANs","created":"2021-03-18","cited_by_count":55,"area":null},{"id":"2112.02424","title":"Variational Wasserstein gradient flow","created":"2021-12-04","cited_by_count":53,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51,"area":null},{"id":"2206.06169","title":"Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems","created":"2022-06-13","cited_by_count":51,"area":null},{"id":"2106.01413","title":"Rectangular Flows for Manifold Learning","created":"2021-06-02","cited_by_count":50,"area":null},{"id":"2308.12770","title":"WavMark: Watermarking for Audio Generation","created":"2023-08-24","cited_by_count":50,"area":null},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2106.04627","title":"Densely connected normalizing flows","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2105.11982","title":"Quantifying Uncertainty in Deep Spatiotemporal Forecasting","created":"2021-05-25","cited_by_count":48,"area":null},{"id":"2207.02127","title":"A survey of multimodal deep generative models","created":"2022-07-05","cited_by_count":47,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2207.05315","title":"CANF-VC: Conditional Augmented Normalizing Flows for Video Compression","created":"2022-07-12","cited_by_count":46,"area":null}],"next_cursor":"100"}