{"total":187,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863,"area":"diffusion"},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513,"area":null},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408,"area":null},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334,"area":null},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312,"area":null},{"id":"2403.15378","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","created":"2024-03-22","cited_by_count":300,"area":null},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291,"area":"diffusion"},{"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":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254,"area":null},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203,"area":null},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191,"area":null},{"id":"2211.11319","title":"VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models","created":"2022-11-21","cited_by_count":112,"area":"diffusion"},{"id":"2303.17569","title":"Iterative Prompt Learning for Unsupervised Backlit Image Enhancement","created":"2023-03-30","cited_by_count":107,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"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":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2312.16476","title":"SVGDreamer: Text Guided SVG Generation with Diffusion Model","created":"2023-12-27","cited_by_count":76,"area":"diffusion"},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75,"area":null},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66,"area":null},{"id":"2211.17256","title":"CLIPascene: Scene Sketching with Different Types and Levels of Abstraction","created":"2022-11-30","cited_by_count":64,"area":null},{"id":"2303.01818","title":"Word-As-Image for Semantic Typography","created":"2023-03-03","cited_by_count":63,"area":null},{"id":"2203.00386","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","created":"2022-03-01","cited_by_count":60,"area":null},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59,"area":"diffusion"},{"id":"2202.05822","title":"CLIPasso: Semantically-Aware Object Sketching","created":"2022-02-11","cited_by_count":57,"area":null},{"id":"2205.08535","title":"AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars","created":"2022-05-17","cited_by_count":55,"area":null},{"id":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54,"area":null},{"id":"2306.14685","title":"DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models","created":"2023-06-26","cited_by_count":54,"area":"diffusion"},{"id":"2303.00304","title":"Renderable Neural Radiance Map for Visual Navigation","created":"2023-03-01","cited_by_count":51,"area":null},{"id":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48,"area":null},{"id":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47,"area":null},{"id":"2210.15929","title":"Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training","created":"2022-10-28","cited_by_count":45,"area":null},{"id":"2306.10008","title":"CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search","created":"2023-06-16","cited_by_count":43,"area":null},{"id":"2502.01105","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","created":"2025-02-03","cited_by_count":43,"area":"diffusion"},{"id":"2206.04382","title":"CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes","created":"2022-06-09","cited_by_count":41,"area":null},{"id":"2410.00741","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","created":"2024-10-01","cited_by_count":41,"area":null},{"id":"2109.08857","title":"Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts","created":"2021-09-18","cited_by_count":40,"area":null},{"id":"2212.02469","title":"One-shot Implicit Animatable Avatars with Model-based Priors","created":"2022-12-05","cited_by_count":38,"area":null},{"id":"2406.06062","title":"ProcessPainter: Learn Painting Process from Sequence Data","created":"2024-06-10","cited_by_count":38,"area":null},{"id":"2406.09417","title":"Rethinking Score Distillation as a Bridge Between Image Distributions","created":"2024-06-13","cited_by_count":38,"area":"diffusion"},{"id":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38,"area":"diffusion"},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38,"area":"diffusion"},{"id":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37,"area":null},{"id":"2307.09781","title":"Text2Layer: Layered Image Generation using Latent Diffusion Model","created":"2023-07-19","cited_by_count":37,"area":"diffusion"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2111.13333","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","created":"2021-11-26","cited_by_count":34,"area":"mllm"},{"id":"2212.02122","title":"CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics","created":"2022-12-05","cited_by_count":34,"area":null},{"id":"2405.10317","title":"Text-to-Vector Generation with Neural Path Representation","created":"2024-05-16","cited_by_count":33,"area":null},{"id":"2212.11263","title":"3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions","created":"2022-12-21","cited_by_count":32,"area":null},{"id":"2411.17673","title":"SketchAgent: Language-Driven Sequential Sketch Generation","created":"2024-11-26","cited_by_count":31,"area":null},{"id":"2209.13360","title":"Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion","created":"2022-09-27","cited_by_count":30,"area":"diffusion"},{"id":"2202.12362","title":"StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation","created":"2022-02-24","cited_by_count":28,"area":null},{"id":"2203.04705","title":"FlexIT: Towards Flexible Semantic Image Translation","created":"2022-03-09","cited_by_count":28,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2308.02552","title":"Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion","created":"2023-08-02","cited_by_count":27,"area":"diffusion"},{"id":"2303.09604","title":"DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion","created":"2023-03-16","cited_by_count":26,"area":"diffusion"},{"id":"2205.10752","title":"Covariance Matrix Adaptation MAP-Annealing","created":"2022-05-22","cited_by_count":25,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2503.11509","title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","created":"2025-03-14","cited_by_count":24,"area":null},{"id":"2304.14630","title":"Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model","created":"2023-04-28","cited_by_count":21,"area":null},{"id":"2412.17799","title":"Automating the Search for Artificial Life with Foundation Models","created":"2024-12-23","cited_by_count":20,"area":null},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2311.15421","title":"Wired Perspectives: Multi-View Wire Art Embraces Generative AI","created":"2023-11-26","cited_by_count":17,"area":null},{"id":"2405.15217","title":"NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation","created":"2024-05-24","cited_by_count":17,"area":"diffusion"},{"id":"2501.03992","title":"NeuralSVG: An Implicit Representation for Text-to-Vector Generation","created":"2025-01-07","cited_by_count":17,"area":null},{"id":"2310.01819","title":"TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling","created":"2023-10-03","cited_by_count":16,"area":null},{"id":"2111.03133","title":"StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis","created":"2021-11-04","cited_by_count":15,"area":null},{"id":"2508.07766","title":"UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models","created":"2025-08-11","cited_by_count":15,"area":"mllm"},{"id":"2202.13562","title":"Name Your Style: An Arbitrary Artist-aware Image Style Transfer","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2312.04248","title":"TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes","created":"2023-12-07","cited_by_count":14,"area":null},{"id":"2412.10488","title":"SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformers","created":"2024-12-13","cited_by_count":14,"area":null},{"id":"2502.08642","title":"SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation","created":"2025-02-12","cited_by_count":14,"area":"mllm"},{"id":"2508.09168","title":"SVGen: Interpretable Vector Graphics Generation with Large Language Models","created":"2025-08-06","cited_by_count":14,"area":null},{"id":"2510.11341","title":"InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models","created":"2025-10-13","cited_by_count":14,"area":"mllm"},{"id":"2206.12396","title":"Text-Driven Stylization of Video Objects","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2305.17489","title":"Text-to-image Editing by Image Information Removal","created":"2023-05-27","cited_by_count":12,"area":"diffusion"},{"id":"2306.16805","title":"CLIPAG: Towards Generator-Free Text-to-Image Generation","created":"2023-06-29","cited_by_count":12,"area":null},{"id":"2604.20730","title":"Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback","created":"2026-04-22","cited_by_count":12,"area":"mllm"},{"id":"2205.03146","title":"CLIP-CLOP: CLIP-Guided Collage and Photomontage","created":"2022-05-06","cited_by_count":11,"area":null},{"id":"2311.09822","title":"MAM-E: Mammographic synthetic image generation with diffusion models","created":"2023-11-16","cited_by_count":11,"area":"diffusion"},{"id":"2408.15741","title":"Segmentation-guided Layer-wise Image Vectorization with Gradient Fills","created":"2024-08-28","cited_by_count":11,"area":null},{"id":"2308.14191","title":"SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation","created":"2023-08-27","cited_by_count":10,"area":"diffusion"},{"id":"2205.01605","title":"Toward Modeling Creative Processes for Algorithmic Painting","created":"2022-05-03","cited_by_count":9,"area":null},{"id":"2307.14611","title":"TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2405.15305","title":"Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2508.15535","title":"Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors","created":"2025-08-21","cited_by_count":9,"area":null},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2506.21101","title":"OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2512.10894","title":"DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance","created":"2025-12-11","cited_by_count":8,"area":"mllm"},{"id":"2306.06441","title":"Image Vectorization: a Review","created":"2023-06-10","cited_by_count":7,"area":null},{"id":"2405.02962","title":"VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors","created":"2024-05-05","cited_by_count":7,"area":null},{"id":"2112.08930","title":"Intelli-Paint: Towards Developing Human-like Painting Agents","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2302.11710","title":"Controlled and Conditional Text to Image Generation with Diffusion Prior","created":"2023-02-23","cited_by_count":6,"area":"diffusion"},{"id":"2406.19859","title":"MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis","created":"2024-06-28","cited_by_count":6,"area":null},{"id":"2412.12223","title":"Can video generation replace cinematographers? Research on the cinematic language of generated video","created":"2024-12-16","cited_by_count":6,"area":"diffusion"},{"id":"2503.19791","title":"SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2605.01517","title":"VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation","created":"2026-05-02","cited_by_count":6,"area":null},{"id":"2205.07301","title":"Conditional Vector Graphics Generation for Music Cover Images","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2304.08204","title":"Learning Geometry-aware Representations by Sketching","created":"2023-04-17","cited_by_count":5,"area":null}],"next_cursor":"100"}