{"total":264,"rows":[{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345,"area":null},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313,"area":null},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228,"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":"2305.01644","title":"Key-Locked Rank One Editing for Text-to-Image Personalization","created":"2023-05-02","cited_by_count":194,"area":null},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185,"area":null},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"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":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129,"area":null},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","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":"2304.07090","title":"Delta Denoising Score","created":"2023-04-14","cited_by_count":121,"area":null},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112,"area":null},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112,"area":null},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105,"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":"2303.12218","title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","created":"2023-03-21","cited_by_count":101,"area":null},{"id":"2310.17590","title":"Noise-Free Score Distillation","created":"2023-10-26","cited_by_count":99,"area":null},{"id":"2504.07963","title":"PixelFlow: Pixel-Space Generative Models with Flow","created":"2025-04-10","cited_by_count":97,"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":"2212.10562","title":"Character-Aware Models Improve Visual Text Rendering","created":"2022-12-20","cited_by_count":92,"area":null},{"id":"2402.10128","title":"GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering","created":"2024-02-15","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":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"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":"2307.06925","title":"Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models","created":"2023-07-13","cited_by_count":85,"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":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68,"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":"2305.16494","title":"Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64,"area":null},{"id":"2311.17857","title":"Gaussian Shell Maps for Efficient 3D Human Generation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60,"area":null},{"id":"2211.08095","title":"Will Large-scale Generative Models Corrupt Future Datasets?","created":"2022-11-15","cited_by_count":59,"area":null},{"id":"2302.02412","title":"Mixture of Diffusers for scene composition and high resolution image generation","created":"2023-02-05","cited_by_count":56,"area":null},{"id":"2305.08252","title":"Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity","created":"2023-05-14","cited_by_count":56,"area":null},{"id":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54,"area":null},{"id":"2407.02430","title":"Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects","created":"2024-07-02","cited_by_count":52,"area":null},{"id":"2405.13870","title":"FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition","created":"2024-05-22","cited_by_count":49,"area":null},{"id":"2411.15466","title":"Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator","created":"2024-11-23","cited_by_count":48,"area":null},{"id":"2504.06632","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","created":"2025-04-09","cited_by_count":46,"area":null},{"id":"2411.17189","title":"PhysMotion: Physics-Grounded Dynamics From a Single Image","created":"2024-11-26","cited_by_count":45,"area":null},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2310.05590","title":"Perceptual Artifacts Localization for Image Synthesis Tasks","created":"2023-10-09","cited_by_count":43,"area":null},{"id":"2404.16771","title":"ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving","created":"2024-04-25","cited_by_count":43,"area":null},{"id":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2403.00483","title":"RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization","created":"2024-03-01","cited_by_count":39,"area":null},{"id":"2405.08246","title":"Compositional Text-to-Image Generation with Dense Blob Representations","created":"2024-05-14","cited_by_count":38,"area":null},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37,"area":null},{"id":"2212.00932","title":"ObjectStitch: Generative Object Compositing","created":"2022-12-02","cited_by_count":36,"area":null},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"area":null},{"id":"2405.01536","title":"Customizing Text-to-Image Models with a Single Image Pair","created":"2024-05-02","cited_by_count":36,"area":null},{"id":"2407.02329","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","created":"2024-07-02","cited_by_count":35,"area":null},{"id":"2303.17870","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","created":"2023-03-31","cited_by_count":34,"area":null},{"id":"2306.07200","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","created":"2023-06-12","cited_by_count":34,"area":null},{"id":"2306.00738","title":"ReFACT: Updating Text-to-Image Models by Editing the Text Encoder","created":"2023-06-01","cited_by_count":32,"area":null},{"id":"2506.06276","title":"STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis","created":"2025-06-06","cited_by_count":32,"area":null},{"id":"2310.09031","title":"MINDE: Mutual Information Neural Diffusion Estimation","created":"2023-10-13","cited_by_count":31,"area":null},{"id":"2403.18551","title":"Attention Calibration for Disentangled Text-to-Image Personalization","created":"2024-03-27","cited_by_count":31,"area":null},{"id":"2412.17098","title":"DreamOmni: Unified Image Generation and Editing","created":"2024-12-22","cited_by_count":30,"area":null},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28,"area":null},{"id":"2503.12885","title":"DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models","created":"2025-03-17","cited_by_count":28,"area":null},{"id":"2407.20337","title":"Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities","created":"2024-07-29","cited_by_count":27,"area":null},{"id":"2307.14331","title":"Visual Instruction Inversion: Image Editing via Visual Prompting","created":"2023-07-26","cited_by_count":26,"area":null},{"id":"2309.05330","title":"Diff-Privacy: Diffusion-based Face Privacy Protection","created":"2023-09-11","cited_by_count":26,"area":null},{"id":"2310.10644","title":"TOSS:High-quality Text-guided Novel View Synthesis from a Single Image","created":"2023-10-16","cited_by_count":26,"area":null},{"id":"2404.06451","title":"SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2405.18199","title":"Adam with model exponential moving average is effective for nonconvex optimization","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2503.01103","title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2311.17083","title":"CLiC: Concept Learning in Context","created":"2023-11-28","cited_by_count":20,"area":null},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2408.14826","title":"Alfie: Democratising RGBA Image Generation With No $$$","created":"2024-08-27","cited_by_count":20,"area":null},{"id":"2502.13081","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey","created":"2025-02-18","cited_by_count":20,"area":null},{"id":"2403.09093","title":"Desigen: A Pipeline for Controllable Design Template Generation","created":"2024-03-14","cited_by_count":19,"area":null},{"id":"2409.11406","title":"Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion","created":"2024-09-17","cited_by_count":19,"area":null},{"id":"2504.21682","title":"Visual Text Processing: A Comprehensive Review and Unified Evaluation","created":"2025-04-30","cited_by_count":19,"area":null},{"id":"2303.16765","title":"MDP: A Generalized Framework for Text-Guided Image Editing by Manipulating the Diffusion Path","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2307.05134","title":"TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation","created":"2023-07-11","cited_by_count":18,"area":null},{"id":"2311.04315","title":"A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization","created":"2023-11-07","cited_by_count":18,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"area":null},{"id":"2405.18025","title":"Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2411.16752","title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","created":"2024-11-24","cited_by_count":18,"area":null},{"id":"2505.02370","title":"SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing","created":"2025-05-05","cited_by_count":18,"area":null},{"id":"2507.23372","title":"UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries","created":"2025-07-31","cited_by_count":18,"area":null},{"id":"2306.00800","title":"FigGen: Text to Scientific Figure Generation","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2408.12128","title":"Diffusion-Based Visual Art Creation: A Survey and New Perspectives","created":"2024-08-22","cited_by_count":17,"area":null},{"id":"2501.03992","title":"NeuralSVG: An Implicit Representation for Text-to-Vector Generation","created":"2025-01-07","cited_by_count":17,"area":null},{"id":"2404.04890","title":"A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals","created":"2024-04-07","cited_by_count":16,"area":null}],"next_cursor":"100"}