{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201},{"id":"2106.14843","title":"CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders","created":"2021-06-28","cited_by_count":187},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2401.06591","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","created":"2024-01-12","cited_by_count":125},{"id":"2102.02798","title":"Im2Vec: Synthesizing Vector Graphics without Vector Supervision","created":"2021-02-04","cited_by_count":116},{"id":"2211.11319","title":"VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models","created":"2022-11-21","cited_by_count":112},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","cited_by_count":102},{"id":"1904.02632","title":"A Learned Representation for Scalable Vector Graphics","created":"2019-04-04","cited_by_count":91},{"id":"2206.04655","title":"Towards Layer-wise Image Vectorization","created":"2022-06-09","cited_by_count":79},{"id":"2312.16476","title":"SVGDreamer: Text Guided SVG Generation with Diffusion Model","created":"2023-12-27","cited_by_count":76},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75},{"id":"2504.06263","title":"OmniSVG: A Unified Scalable Vector Graphics Generation Model","created":"2025-04-08","cited_by_count":74},{"id":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66},{"id":"2306.14685","title":"DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models","created":"2023-06-26","cited_by_count":54},{"id":"2502.01105","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","created":"2025-02-03","cited_by_count":43},{"id":"2505.20793","title":"Rendering-Aware Reinforcement Learning for Vector Graphics Generation","created":"2025-05-27","cited_by_count":39},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38},{"id":"2303.14585","title":"DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality","created":"2023-03-25","cited_by_count":27},{"id":"2401.05293","title":"Score Distillation Sampling with Learned Manifold Corrective","created":"2024-01-10","cited_by_count":27},{"id":"2401.17093","title":"StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis","created":"2024-01-30","cited_by_count":26},{"id":"2404.13710","title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities","created":"2024-04-21","cited_by_count":26},{"id":"2405.15217","title":"NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation","created":"2024-05-24","cited_by_count":17},{"id":"2501.03992","title":"NeuralSVG: An Implicit Representation for Text-to-Vector Generation","created":"2025-01-07","cited_by_count":17},{"id":"2305.10462","title":"DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representation","created":"2023-05-17","cited_by_count":16},{"id":"2506.03139","title":"SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation","created":"2025-06-03","cited_by_count":16},{"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},{"id":"2508.09168","title":"SVGen: Interpretable Vector Graphics Generation with Large Language Models","created":"2025-08-06","cited_by_count":14},{"id":"2510.11341","title":"InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models","created":"2025-10-13","cited_by_count":14},{"id":"2502.19453","title":"SVGEditBench V2: A Benchmark for Instruction-based SVG Editing","created":"2025-02-26","cited_by_count":11},{"id":"2306.06094","title":"Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding","created":"2023-06-09","cited_by_count":10},{"id":"2405.02962","title":"VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors","created":"2024-05-05","cited_by_count":7},{"id":"2603.29852","title":"VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing","created":"2026-02-22","cited_by_count":5},{"id":"2410.05991","title":"Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision","created":"2024-10-08","cited_by_count":3},{"id":"2410.15760","title":"DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorization","created":"2024-10-21","cited_by_count":2},{"id":"2509.07127","title":"SVGauge: Towards Human-Aligned Evaluation for SVG Generation","created":"2025-09-08","cited_by_count":1},{"id":"2604.05072","title":"Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling","created":"2026-04-06","cited_by_count":1},{"id":"2608.01977","title":"SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation","created":"2026-08-03","cited_by_count":1},{"id":"2608.21893","title":"A Scalable Vector Graphics Latent Space","created":"2026-08-22","cited_by_count":1}],"next_cursor":null}