{"total":40,"rows":[{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285,"area":null},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137,"area":null},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45,"area":null},{"id":"2408.01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","created":"2024-08-02","cited_by_count":42,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2209.04145","title":"ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2022-09-09","cited_by_count":27,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2209.09898","title":"Text2Light: Zero-Shot Text-Driven HDR Panorama Generation","created":"2022-09-20","cited_by_count":24,"area":null},{"id":"2210.12977","title":"Language-free Training for Zero-shot Video Grounding","created":"2022-10-24","cited_by_count":22,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"id":"2301.01413","title":"Attribute-Centric Compositional Text-to-Image Generation","created":"2023-01-04","cited_by_count":19,"area":null},{"id":"2307.15904","title":"Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Images","created":"2023-07-29","cited_by_count":19,"area":null},{"id":"2305.02541","title":"Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder","created":"2023-05-04","cited_by_count":18,"area":null},{"id":"2408.05974","title":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","created":"2024-08-12","cited_by_count":11,"area":null},{"id":"2211.15045","title":"CLIP2GAN: Towards Bridging Text with the Latent Space of GANs","created":"2022-11-28","cited_by_count":8,"area":null},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2210.02291","title":"Progressive Text-to-Image Generation","created":"2022-10-05","cited_by_count":4,"area":null},{"id":"2303.15181","title":"DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2312.07951","title":"Semantic-aware Data Augmentation for Text-to-image Synthesis","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2408.09594","title":"Moonshine: Distilling Game Content Generators into Steerable Generative Models","created":"2024-08-18","cited_by_count":4,"area":null},{"id":"2504.03563","title":"PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2505.23161","title":"Implicit Inversion turns CLIP into a Decoder","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2409.13496","title":"DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurring","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2506.08854","title":"Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2210.15235","title":"SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2304.13742","title":"TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2305.14969","title":"MMNet: Multi-Mask Network for Referring Image Segmentation","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2311.03314","title":"FATE: Feature-Agnostic Transformer-based Encoder for learning generalized embedding spaces in flow cytometry data","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2407.03893","title":"Do Generalised Classifiers really work on Human Drawn Sketches?","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2410.09691","title":"Robust 3D Point Clouds Classification based on Declarative Defenders","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2308.09779","title":"EAVL: Explicitly Align Vision and Language for Referring Image Segmentation","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2404.13579","title":"LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions","created":"2024-04-21","cited_by_count":1,"area":null},{"id":"2405.11205","title":"Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2408.03001","title":"One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2411.12319","title":"CLIP Unreasonable Potential in Single-Shot Face Recognition","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2510.18795","title":"ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2303.16105","title":"Variational Distribution Learning for Unsupervised Text-to-Image Generation","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2506.18544","title":"Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2511.20274","title":"SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking","created":"2025-11-25","cited_by_count":0,"area":null}],"next_cursor":null}