{"total":4122,"rows":[{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742,"area":null},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045,"area":null},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985,"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":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385,"area":null},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341,"area":null},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328,"area":null},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314,"area":null},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307,"area":null},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287,"area":null},{"id":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259,"area":null},{"id":"2303.15140","title":"SimpleNet: A Simple Network for Image Anomaly Detection and Localization","created":"2023-03-27","cited_by_count":256,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235,"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":"2401.03890","title":"A Survey on 3D Gaussian Splatting","created":"2024-01-08","cited_by_count":224,"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":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220,"area":null},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218,"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":"2301.09515","title":"StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis","created":"2023-01-23","cited_by_count":212,"area":null},{"id":"2304.00186","title":"Subject-driven Text-to-Image Generation via Apprenticeship Learning","created":"2023-04-01","cited_by_count":212,"area":null},{"id":"2307.01097","title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","created":"2023-07-03","cited_by_count":212,"area":null},{"id":"2307.03838","title":"RADAR: Robust AI-Text Detection via Adversarial Learning","created":"2023-07-07","cited_by_count":190,"area":null},{"id":"2203.13777","title":"Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion","created":"2022-03-25","cited_by_count":185,"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":"2208.09910","title":"Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation","created":"2022-08-21","cited_by_count":178,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164,"area":null},{"id":"2307.14126","title":"Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling","created":"2023-07-26","cited_by_count":163,"area":null},{"id":"2302.01133","title":"SceneScape: Text-Driven Consistent Scene Generation","created":"2023-02-02","cited_by_count":160,"area":null},{"id":"2205.13218","title":"A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning","created":"2022-05-26","cited_by_count":154,"area":null},{"id":"2303.17015","title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","created":"2023-03-29","cited_by_count":152,"area":null},{"id":"2203.10446","title":"A 3D Generative Model for Structure-Based Drug Design","created":"2022-03-20","cited_by_count":149,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142,"area":null},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136,"area":null},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135,"area":null},{"id":"2306.06101","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","created":"2023-06-09","cited_by_count":133,"area":null},{"id":"2305.04461","title":"Locally Attentional SDF Diffusion for Controllable 3D Shape Generation","created":"2023-05-08","cited_by_count":130,"area":null},{"id":"2212.03293","title":"Diffusion-SDF: Text-to-Shape via Voxelized Diffusion","created":"2022-12-06","cited_by_count":128,"area":null},{"id":"2303.07205","title":"The Science of Detecting LLM-Generated Texts","created":"2023-02-04","cited_by_count":128,"area":null},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","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":"2302.04062","title":"Machine Learning for Synthetic Data Generation: A Review","created":"2023-02-08","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":"2305.11487","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","created":"2023-05-19","cited_by_count":115,"area":null},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2210.04888","title":"EVA3D: Compositional 3D Human Generation from 2D Image Collections","created":"2022-10-10","cited_by_count":111,"area":null},{"id":"2303.11851","title":"Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation","created":"2023-03-21","cited_by_count":110,"area":null},{"id":"2310.14724","title":"A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions","created":"2023-10-23","cited_by_count":105,"area":null},{"id":"2411.15633","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","created":"2024-11-23","cited_by_count":105,"area":null},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104,"area":null},{"id":"2302.11803","title":"A Comprehensive Survey on Source-free Domain Adaptation","created":"2023-02-23","cited_by_count":104,"area":null},{"id":"2406.02917","title":"A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks","created":"2024-06-05","cited_by_count":104,"area":null},{"id":"2408.02555","title":"MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization","created":"2024-08-05","cited_by_count":104,"area":null},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","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":"2409.12957","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion","created":"2024-09-19","cited_by_count":101,"area":null},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100,"area":null},{"id":"2307.07494","title":"TALL: Thumbnail Layout for Deepfake Video Detection","created":"2023-07-14","cited_by_count":100,"area":null},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99,"area":null},{"id":"2204.06890","title":"Clothes-Changing Person Re-identification with RGB Modality Only","created":"2022-04-14","cited_by_count":98,"area":null},{"id":"2303.17480","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","created":"2023-03-29","cited_by_count":98,"area":null},{"id":"2203.14216","title":"Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution","created":"2022-03-27","cited_by_count":96,"area":null},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94,"area":null},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94,"area":null},{"id":"2305.02195","title":"CALM: Conditional Adversarial Latent Models for Directable Virtual Characters","created":"2023-05-02","cited_by_count":94,"area":null},{"id":"2205.13914","title":"3DILG: Irregular Latent Grids for 3D Generative Modeling","created":"2022-05-27","cited_by_count":93,"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":"2211.08064","title":"Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91,"area":null},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88,"area":null},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88,"area":null},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"area":null},{"id":"2506.07977","title":"OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation","created":"2025-06-09","cited_by_count":87,"area":null},{"id":"2206.08213","title":"A Closer Look at Smoothness in Domain Adversarial Training","created":"2022-06-16","cited_by_count":85,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"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":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84,"area":null},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83,"area":null},{"id":"2203.12691","title":"Learning to generate line drawings that convey geometry and semantics","created":"2022-03-23","cited_by_count":83,"area":null},{"id":"2203.15685","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","created":"2022-03-29","cited_by_count":83,"area":null},{"id":"2206.07769","title":"HyperImpute: Generalized Iterative Imputation with Automatic Model Selection","created":"2022-06-15","cited_by_count":83,"area":null},{"id":"2207.11148","title":"InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images","created":"2022-07-22","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":"2404.06903","title":"DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting","created":"2024-04-10","cited_by_count":82,"area":null}],"next_cursor":"100"}