{"total":121,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702,"area":"wm"},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300,"area":"diffusion"},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492,"area":null},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313,"area":"diffusion"},{"id":"2303.17591","title":"Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models","created":"2023-03-30","cited_by_count":301,"area":"diffusion"},{"id":"2307.06949","title":"HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models","created":"2023-07-13","cited_by_count":225,"area":null},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212,"area":"diffusion"},{"id":"2304.00186","title":"Subject-driven Text-to-Image Generation via Apprenticeship Learning","created":"2023-04-01","cited_by_count":212,"area":null},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208,"area":"diffusion"},{"id":"2305.18274","title":"Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors","created":"2023-05-29","cited_by_count":160,"area":"diffusion"},{"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":"2112.09130","title":"Ensembling Off-the-shelf Models for GAN Training","created":"2021-12-16","cited_by_count":86,"area":null},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75,"area":"diffusion"},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75,"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":"2207.13038","title":"Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models","created":"2022-07-26","cited_by_count":64,"area":"rag"},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64,"area":"distill"},{"id":"2303.09319","title":"Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation","created":"2023-03-16","cited_by_count":60,"area":"diffusion"},{"id":"2202.12692","title":"Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANs","created":"2022-02-25","cited_by_count":55,"area":null},{"id":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"area":"diffusion"},{"id":"2212.02409","title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","created":"2022-12-05","cited_by_count":49,"area":null},{"id":"2303.01416","title":"3D generation on ImageNet","created":"2023-03-02","cited_by_count":47,"area":null},{"id":"2305.18286","title":"Photoswap: Personalized Subject Swapping in Images","created":"2023-05-29","cited_by_count":47,"area":null},{"id":"2308.04249","title":"MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion","created":"2023-08-08","cited_by_count":47,"area":null},{"id":"2208.11126","title":"Retrieval-based Controllable Molecule Generation","created":"2022-08-23","cited_by_count":44,"area":null},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41,"area":null},{"id":"2206.09479","title":"StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis","created":"2022-06-19","cited_by_count":38,"area":null},{"id":"2202.12211","title":"Self-Distilled StyleGAN: Towards Generation from Internet Photos","created":"2022-02-24","cited_by_count":37,"area":null},{"id":"2204.11824","title":"Semi-Parametric Neural Image Synthesis","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2210.06462","title":"Self-Guided Diffusion Models","created":"2022-10-12","cited_by_count":37,"area":"diffusion"},{"id":"2302.10586","title":"Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels","created":"2023-02-21","cited_by_count":37,"area":"diffusion"},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37,"area":null},{"id":"2202.14020","title":"State-of-the-Art in the Architecture, Methods and Applications of StyleGAN","created":"2022-02-28","cited_by_count":34,"area":null},{"id":"2305.11560","title":"Brain Captioning: Decoding human brain activity into images and text","created":"2023-05-19","cited_by_count":34,"area":"diffusion"},{"id":"2310.00158","title":"Feedback-guided Data Synthesis for Imbalanced Classification","created":"2023-09-29","cited_by_count":33,"area":"synth"},{"id":"2304.05818","title":"Gradient-Free Textual Inversion","created":"2023-04-12","cited_by_count":29,"area":null},{"id":"2203.04705","title":"FlexIT: Towards Flexible Semantic Image Translation","created":"2022-03-09","cited_by_count":28,"area":null},{"id":"2212.00362","title":"Why Are Conditional Generative Models Better Than Unconditional Ones?","created":"2022-12-01","cited_by_count":28,"area":"diffusion"},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2112.00718","title":"Improving GAN Equilibrium by Raising Spatial Awareness","created":"2021-12-01","cited_by_count":22,"area":null},{"id":"2203.01993","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2309.00627","title":"Through their eyes: multi-subject Brain Decoding with simple alignment techniques","created":"2023-08-01","cited_by_count":21,"area":null},{"id":"2306.05423","title":"ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process","created":"2023-06-08","cited_by_count":20,"area":"diffusion"},{"id":"2407.03300","title":"DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents","created":"2024-07-03","cited_by_count":20,"area":"diffusion"},{"id":"2307.08283","title":"Complexity Matters: Rethinking the Latent Space for Generative Modeling","created":"2023-07-17","cited_by_count":19,"area":"diffusion"},{"id":"2307.14397","title":"A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot","created":"2023-07-26","cited_by_count":19,"area":null},{"id":"2506.08257","title":"Highly Compressed Tokenizer Can Generate Without Training","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2306.10169","title":"Meta-Personalizing Vision-Language Models to Find Named Instances in Video","created":"2023-06-16","cited_by_count":16,"area":"mllm"},{"id":"2405.04457","title":"Towards Geographic Inclusion in the Evaluation of Text-to-Image Models","created":"2024-05-07","cited_by_count":16,"area":null},{"id":"2505.11131","title":"One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework","created":"2025-05-16","cited_by_count":16,"area":"diffusion"},{"id":"2401.00430","title":"Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2203.09554","title":"CoGS: Controllable Generation and Search from Sketch and Style","created":"2022-03-17","cited_by_count":14,"area":null},{"id":"2402.02972","title":"Retrieval-Augmented Score Distillation for Text-to-3D Generation","created":"2024-02-05","cited_by_count":14,"area":"rag"},{"id":"2304.05866","title":"NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2211.05385","title":"GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning","created":"2022-11-10","cited_by_count":9,"area":null},{"id":"2307.16879","title":"Image Synthesis under Limited Data: A Survey and Taxonomy","created":"2023-07-31","cited_by_count":9,"area":null},{"id":"2308.06198","title":"DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity","created":"2023-08-11","cited_by_count":9,"area":null},{"id":"2312.00079","title":"HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models","created":"2023-11-30","cited_by_count":9,"area":"diffusion"},{"id":"2405.20024","title":"Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Survey","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2411.19528","title":"RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2303.14730","title":"Joint fMRI Decoding and Encoding with Latent Embedding Alignment","created":"2023-03-26","cited_by_count":8,"area":null},{"id":"2210.03116","title":"Content-Based Search for Deep Generative Models","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2303.09677","title":"Instance-Conditioned GAN Data Augmentation for Representation Learning","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2304.01999","title":"Revisiting the Evaluation of Image Synthesis with GANs","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2411.13378","title":"Quantum-Brain: Quantum-Inspired Neural Network Approach to Vision-Brain Understanding","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2304.01515","title":"Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models","created":"2023-04-04","cited_by_count":6,"area":"inference"},{"id":"2412.12788","title":"RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning","created":"2024-12-17","cited_by_count":6,"area":"rag"},{"id":"2303.06464","title":"PARASOL: Parametric Style Control for Diffusion Image Synthesis","created":"2023-03-11","cited_by_count":5,"area":"diffusion"},{"id":"2304.13722","title":"Controllable Image Generation via Collage Representations","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2311.08217","title":"Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2311.09753","title":"DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics","created":"2023-11-16","cited_by_count":5,"area":"diffusion"},{"id":"2403.00570","title":"Rethinking cluster-conditioned diffusion models for label-free image synthesis","created":"2024-03-01","cited_by_count":5,"area":"diffusion"},{"id":"2409.03106","title":"Spatial Diffusion for Cell Layout Generation","created":"2024-09-04","cited_by_count":5,"area":"diffusion"},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2412.19494","title":"Retrieval-augmented Generation for GenAI-enabled Semantic Communications","created":"2024-12-27","cited_by_count":5,"area":"rag"},{"id":"2504.06672","title":"RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism","created":"2025-04-09","cited_by_count":5,"area":"rag"},{"id":"2208.08493","title":"Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2304.02321","title":"Few-shot Semantic Image Synthesis with Class Affinity Transfer","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2403.14421","title":"DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning","created":"2024-03-21","cited_by_count":4,"area":"rag"},{"id":"2408.07828","title":"Space-scale Exploration of the Poor Reliability of Deep Learning Models: the Case of the Remote Sensing of Rooftop Photovoltaic Systems","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2211.02798","title":"Local Manifold Augmentation for Multiview Semantic Consistency","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2311.10794","title":"Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression","created":"2023-11-17","cited_by_count":3,"area":"diffusion"},{"id":"2312.14776","title":"Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2403.05966","title":"Can Generative Models Improve Self-Supervised Representation Learning?","created":"2024-03-09","cited_by_count":3,"area":null},{"id":"2409.12099","title":"Brain-Streams: fMRI-to-Image Reconstruction with Multi-modal Guidance","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2502.12794","title":"RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models","created":"2025-02-18","cited_by_count":3,"area":"rag"},{"id":"2506.02697","title":"LayoutRAG: Retrieval-Augmented Model for Content-agnostic Conditional Layout Generation","created":"2025-06-03","cited_by_count":3,"area":"rag"},{"id":"2210.10578","title":"Language Does More Than Describe: On The Lack Of Figurative Speech in Text-To-Image Models","created":"2022-10-19","cited_by_count":2,"area":"diffusion"},{"id":"2301.08455","title":"Spatial Steerability of GANs via Self-Supervision from Discriminator","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2305.07613","title":"Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2310.00357","title":"Structural Adversarial Objectives for Self-Supervised Representation Learning","created":"2023-09-30","cited_by_count":2,"area":null},{"id":"2412.05984","title":"Nested Diffusion Models Using Hierarchical Latent Priors","created":"2024-12-08","cited_by_count":2,"area":"diffusion"},{"id":"2511.22345","title":"Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2602.04908","title":"Temporal Pair Consistency for Variance-Reduced Flow Matching","created":"2026-02-04","cited_by_count":2,"area":"diffusion"},{"id":"2203.16662","title":"Overcoming challenges in leveraging GANs for few-shot data augmentation","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2206.05764","title":"Mining Multi-Label Samples from Single Positive Labels","created":"2022-06-12","cited_by_count":1,"area":null},{"id":"2401.04558","title":"HyperGANStrument: Instrument Sound Synthesis and Editing with Pitch-Invariant Hypernetworks","created":"2024-01-09","cited_by_count":1,"area":null},{"id":"2507.07137","title":"Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge","created":"2025-07-09","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}