{"total":103,"rows":[{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653,"area":null},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648,"area":null},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459,"area":null},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302,"area":null},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264,"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":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204,"area":null},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188,"area":null},{"id":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78,"area":null},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69,"area":null},{"id":"2202.03382","title":"Corrupted Image Modeling for Self-Supervised Visual Pre-Training","created":"2022-02-07","cited_by_count":68,"area":null},{"id":"2108.09274","title":"MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction","created":"2021-08-20","cited_by_count":61,"area":null},{"id":"2304.05919","title":"Hard Patches Mining for Masked Image Modeling","created":"2023-04-12","cited_by_count":57,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2301.01928","title":"Event Camera Data Pre-training","created":"2023-01-05","cited_by_count":50,"area":null},{"id":"2205.13137","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","created":"2022-05-26","cited_by_count":47,"area":null},{"id":"2303.06424","title":"Regularized Vector Quantization for Tokenized Image Synthesis","created":"2023-03-11","cited_by_count":46,"area":null},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41,"area":null},{"id":"2206.03066","title":"Recent Advances for Quantum Neural Networks in Generative Learning","created":"2022-06-07","cited_by_count":39,"area":null},{"id":"2208.13056","title":"Lossy Image Compression with Quantized Hierarchical VAEs","created":"2022-08-27","cited_by_count":35,"area":null},{"id":"2210.01941","title":"SIMPLE: A Gradient Estimator for $k$-Subset Sampling","created":"2022-10-04","cited_by_count":34,"area":null},{"id":"2302.08899","title":"QARV: Quantization-Aware ResNet VAE for Lossy Image Compression","created":"2023-02-16","cited_by_count":32,"area":null},{"id":"2205.07417","title":"Transformers in 3D Point Clouds: A Survey","created":"2022-05-16","cited_by_count":31,"area":null},{"id":"2207.10228","title":"MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis","created":"2022-07-20","cited_by_count":31,"area":null},{"id":"2211.08887","title":"Stare at What You See: Masked Image Modeling without Reconstruction","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2106.04258","title":"Interpretable agent communication from scratch (with a generic visual processor emerging on the side)","created":"2021-06-08","cited_by_count":25,"area":null},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22,"area":null},{"id":"2408.10906","title":"ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining","created":"2024-08-20","cited_by_count":21,"area":null},{"id":"2210.12261","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2306.12330","title":"ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data","created":"2023-06-21","cited_by_count":18,"area":null},{"id":"2312.09597","title":"Deep Generative Models for Detector Signature Simulation: A Taxonomic Review","created":"2023-12-15","cited_by_count":18,"area":null},{"id":"2303.11325","title":"GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2204.00989","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","created":"2022-04-03","cited_by_count":16,"area":null},{"id":"2303.15626","title":"A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models","created":"2023-03-27","cited_by_count":16,"area":null},{"id":"2310.05718","title":"EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders","created":"2023-10-09","cited_by_count":16,"area":null},{"id":"2409.00353","title":"RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning","created":"2024-08-31","cited_by_count":15,"area":null},{"id":"2110.05999","title":"DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2311.12569","title":"Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick","created":"2023-11-21","cited_by_count":14,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2305.05026","title":"Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding","created":"2023-05-08","cited_by_count":13,"area":null},{"id":"2202.01334","title":"Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization","created":"2022-02-02","cited_by_count":11,"area":null},{"id":"2311.04453","title":"Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2312.03179","title":"CaloQVAE : Simulating high-energy particle-calorimeter interactions using hybrid quantum-classical generative models","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2108.11644","title":"Hybrid quantum-classical machine learning for generative chemistry and drug design","created":"2021-08-26","cited_by_count":10,"area":null},{"id":"2301.06958","title":"RILS: Masked Visual Reconstruction in Language Semantic Space","created":"2023-01-17","cited_by_count":10,"area":null},{"id":"2211.06841","title":"Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning","created":"2022-11-13","cited_by_count":9,"area":null},{"id":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2107.13132","title":"Unsupervised Learning of Neurosymbolic Encoders","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2405.20959","title":"Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilities","created":"2024-05-31","cited_by_count":8,"area":null},{"id":"2407.10200","title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","created":"2024-07-14","cited_by_count":8,"area":null},{"id":"2411.06959","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2212.06593","title":"FastMIM: Expediting Masked Image Modeling Pre-training for Vision","created":"2022-12-13","cited_by_count":7,"area":null},{"id":"2310.19944","title":"Conditional Unscented Autoencoders for Trajectory Prediction","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2412.18688","title":"Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2106.05970","title":"ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation","created":"2021-06-10","cited_by_count":6,"area":null},{"id":"2208.04554","title":"Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation","created":"2022-08-09","cited_by_count":6,"area":null},{"id":"2210.07430","title":"CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2207.13226","title":"Boosting Point-BERT by Multi-choice Tokens","created":"2022-07-27","cited_by_count":5,"area":null},{"id":"2312.13714","title":"Bootstrap Masked Visual Modeling via Hard Patches Mining","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2402.01399","title":"A Probabilistic Model Behind Self-Supervised Learning","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2404.07603","title":"GLID: Pre-training a Generalist Encoder-Decoder Vision Model","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2411.15648","title":"Sample- and Parameter-Efficient Auto-Regressive Image Models","created":"2024-11-23","cited_by_count":5,"area":null},{"id":"2305.17262","title":"Im-Promptu: In-Context Composition from Image Prompts","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2306.05138","title":"Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2410.22870","title":"Conditioned quantum-assisted deep generative surrogate for particle-calorimeter interactions","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2111.01785","title":"PatchGame: Learning to Signal Mid-level Patches in Referential Games","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2209.06067","title":"SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds","created":"2022-09-13","cited_by_count":3,"area":null},{"id":"2302.11793","title":"Revisiting the Gumbel-Softmax in MADDPG","created":"2023-02-23","cited_by_count":3,"area":null},{"id":"2403.03391","title":"CoRMF: Criticality-Ordered Recurrent Mean Field Ising Solver","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2407.19889","title":"Self-Supervised Learning for Text Recognition: A Critical Survey","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2106.08571","title":"Discrete Auto-regressive Variational Attention Models for Text Modeling","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2508.05423","title":"Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2508.05507","title":"Revealing Latent Information: A Physics-inspired Self-supervised Pre-training Framework for Noisy and Sparse Events","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2206.09891","title":"Latent Variable Modelling Using Variational Autoencoders: A survey","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2211.00313","title":"RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images","created":"2022-11-01","cited_by_count":1,"area":null},{"id":"2303.04664","title":"Centroid-centered Modeling for Efficient Vision Transformer Pre-training","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2303.12302","title":"Anomaly Detection in Aeronautics Data with Quantum-compatible Discrete Deep Generative Model","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2312.15985","title":"Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agents","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2403.14115","title":"Training point-based deep learning networks for forest segmentation with synthetic data","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2504.03181","title":"MIMRS: A Survey on Masked Image Modeling in Remote Sensing","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.08412","title":"Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-Training","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2505.10344","title":"An Introduction to Discrete Variational Autoencoders","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2601.21775","title":"Differentiable Knapsack and Top-k Operators via Dynamic Programming","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.00919","title":"Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.17131","title":"A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2107.08948","title":"GenRadar: Self-supervised Probabilistic Camera Synthesis based on Radar Frequencies","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2205.02670","title":"Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2309.13235","title":"M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2402.03577","title":"Revisiting the Dataset Bias Problem from a Statistical Perspective","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2410.07840","title":"Improved Variational Inference in Discrete VAEs using Error Correcting Codes","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2504.00395","title":"A Theory of Machine Understanding via the Minimum Description Length Principle","created":"2025-04-01","cited_by_count":0,"area":null}],"next_cursor":"100"}