{"list":"other","total":51,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"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":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"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":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2503.05236","title":"Unified Reward Model for Multimodal Understanding and Generation","created":"2025-03-07","cited_by_count":199},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180},{"id":"2507.21802","title":"MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE","created":"2025-07-29","cited_by_count":178},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154},{"id":"2009.09941","title":"PP-OCR: A Practical Ultra Lightweight OCR System","created":"2020-09-21","cited_by_count":151},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140},{"id":"2305.18259","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","created":"2023-05-29","cited_by_count":131},{"id":"2507.22058","title":"X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again","created":"2025-07-29","cited_by_count":112},{"id":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87},{"id":"2506.07977","title":"OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation","created":"2025-06-09","cited_by_count":87},{"id":"2505.14460","title":"VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank","created":"2025-05-20","cited_by_count":79},{"id":"2506.02161","title":"TIIF-Bench: How Does Your T2I Model Follow Your Instructions?","created":"2025-06-02","cited_by_count":69},{"id":"2503.07703","title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","created":"2025-03-10","cited_by_count":62},{"id":"2411.06686","title":"SeedEdit: Align Image Re-Generation to Image Editing","created":"2024-11-11","cited_by_count":61},{"id":"2312.04884","title":"UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models","created":"2023-12-08","cited_by_count":59},{"id":"2510.15857","title":"BLIP3o-NEXT: Next Frontier of Native Image Generation","created":"2025-10-17","cited_by_count":54},{"id":"2411.15245","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","created":"2024-11-22","cited_by_count":53},{"id":"2308.10755","title":"WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models","created":"2023-08-21","cited_by_count":50},{"id":"2510.22319","title":"GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping","created":"2025-10-25","cited_by_count":49},{"id":"2406.10208","title":"Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering","created":"2024-06-14","cited_by_count":48},{"id":"2504.06632","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","created":"2025-04-09","cited_by_count":46},{"id":"2410.10133","title":"TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control","created":"2024-10-14","cited_by_count":45},{"id":"2107.09313","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","created":"2021-07-20","cited_by_count":43},{"id":"2312.12232","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","created":"2023-12-19","cited_by_count":41},{"id":"2509.09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark","created":"2025-09-11","cited_by_count":38},{"id":"2407.02252","title":"GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models","created":"2024-07-02","cited_by_count":29},{"id":"2405.14701","title":"DreamText: High Fidelity Scene Text Synthesis","created":"2024-05-23","cited_by_count":18},{"id":"2503.21749","title":"LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis","created":"2025-03-27","cited_by_count":15},{"id":"2507.23300","title":"Training-free Geometric Image Editing on Diffusion Models","created":"2025-07-31","cited_by_count":13},{"id":"2506.20168","title":"Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models","created":"2025-06-25","cited_by_count":12},{"id":"2504.09966","title":"SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting","created":"2025-04-14","cited_by_count":2}],"next_cursor":null}