{"total":21,"rows":[{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187,"area":"diffusion"},{"id":"2306.04632","title":"Designing a Better Asymmetric VQGAN for StableDiffusion","created":"2023-06-07","cited_by_count":45,"area":"diffusion"},{"id":"2212.03099","title":"Semantic-Conditional Diffusion Networks for Image Captioning","created":"2022-12-06","cited_by_count":38,"area":"diffusion"},{"id":"2211.13224","title":"Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors","created":"2022-11-23","cited_by_count":34,"area":"diffusion"},{"id":"2304.00500","title":"Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images","created":"2023-04-02","cited_by_count":29,"area":"diffusion"},{"id":"2412.15213","title":"Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution","created":"2024-12-19","cited_by_count":26,"area":"diffusion"},{"id":"2402.10404","title":"Explaining generative diffusion models via visual analysis for interpretable decision-making process","created":"2024-02-16","cited_by_count":17,"area":"diffusion"},{"id":"2211.11694","title":"Exploring Discrete Diffusion Models for Image Captioning","created":"2022-11-21","cited_by_count":16,"area":"diffusion"},{"id":"2305.10722","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","created":"2023-05-18","cited_by_count":14,"area":"diffusion"},{"id":"2311.00618","title":"De-Diffusion Makes Text a Strong Cross-Modal Interface","created":"2023-11-01","cited_by_count":14,"area":"diffusion"},{"id":"2512.17951","title":"SuperFlow: Training Flow Matching Models with RL on the Fly","created":"2025-12-17","cited_by_count":10,"area":"diffusion"},{"id":"2404.10763","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","created":"2024-04-16","cited_by_count":9,"area":"diffusion"},{"id":"2305.18072","title":"Image Captioning with Multi-Context Synthetic Data","created":"2023-05-29","cited_by_count":7,"area":"diffusion"},{"id":"2308.01472","title":"Reverse Stable Diffusion: What prompt was used to generate this image?","created":"2023-08-02","cited_by_count":7,"area":"diffusion"},{"id":"2309.04965","title":"Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning","created":"2023-09-10","cited_by_count":7,"area":"diffusion"},{"id":"2501.00437","title":"Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning","created":"2024-12-31","cited_by_count":7,"area":"diffusion"},{"id":"2305.01855","title":"Multimodal Data Augmentation for Image Captioning using Diffusion Models","created":"2023-05-03","cited_by_count":6,"area":"diffusion"},{"id":"2308.09306","title":"DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability","created":"2023-08-18","cited_by_count":3,"area":"diffusion"},{"id":"2512.01975","title":"SGDiff: Scene Graph Guided Diffusion Model for Image Collaborative SegCaptioning","created":"2025-12-01","cited_by_count":3,"area":"diffusion"},{"id":"2607.06856","title":"Gen4U: Unifying Video Generation and Understanding via Diffusion","created":"2026-07-07","cited_by_count":1,"area":"diffusion"},{"id":"2509.23718","title":"Diff-3DCap: Shape Captioning with Diffusion Models","created":"2025-09-28","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}