{"list":"other","total":67,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2305.16381","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":450},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2406.09403","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models","created":"2024-06-13","cited_by_count":268},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179},{"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":"2508.11630","title":"Thyme: Think Beyond Images","created":"2025-08-15","cited_by_count":167},{"id":"2505.00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","created":"2025-05-01","cited_by_count":166},{"id":"2311.16483","title":"ChartLlama: A Multimodal LLM for Chart Understanding and Generation","created":"2023-11-27","cited_by_count":163},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"id":"2406.18583","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","created":"2024-06-05","cited_by_count":132},{"id":"2503.10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","created":"2025-03-13","cited_by_count":104},{"id":"2508.20751","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","created":"2025-08-28","cited_by_count":92},{"id":"2403.09622","title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering","created":"2024-03-14","cited_by_count":81},{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79},{"id":"2311.01920","title":"ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language","created":"2023-11-03","cited_by_count":73},{"id":"2505.22525","title":"Thinking with Generated Images","created":"2025-05-28","cited_by_count":73},{"id":"2509.08826","title":"RewardDance: Reward Scaling in Visual Generation","created":"2025-09-10","cited_by_count":68},{"id":"2509.23909","title":"EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling","created":"2025-09-28","cited_by_count":64},{"id":"2509.06040","title":"BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models","created":"2025-09-07","cited_by_count":61},{"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":"2504.06632","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","created":"2025-04-09","cited_by_count":46},{"id":"2507.23278","title":"UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing","created":"2025-07-31","cited_by_count":44},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43},{"id":"2308.01095","title":"AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation","created":"2023-08-02","cited_by_count":41},{"id":"2509.06945","title":"Interleaving Reasoning for Better Text-to-Image Generation","created":"2025-09-08","cited_by_count":41},{"id":"2505.11935","title":"ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing","created":"2025-05-17","cited_by_count":32},{"id":"2505.13031","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","created":"2025-05-19","cited_by_count":30},{"id":"2403.08857","title":"DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation","created":"2024-03-13","cited_by_count":26},{"id":"2510.24711","title":"Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance","created":"2025-10-28","cited_by_count":26},{"id":"2404.05673","title":"CoReS: Orchestrating the Dance of Reasoning and Segmentation","created":"2024-04-08","cited_by_count":25},{"id":"2502.14914","title":"CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness","created":"2025-02-19","cited_by_count":25},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23},{"id":"2303.11917","title":"Efficient Decision-based Black-box Patch Attacks on Video Recognition","created":"2023-03-21","cited_by_count":21},{"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},{"id":"2503.16036","title":"Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":19},{"id":"2410.04064","title":"Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback","created":"2024-10-05","cited_by_count":17},{"id":"2507.04218","title":"DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design","created":"2025-07-06","cited_by_count":16},{"id":"2410.14331","title":"ChartifyText: Automated Chart Generation from Data-Involved Texts via LLM","created":"2024-10-18","cited_by_count":7},{"id":"2104.04584","title":"Text2Chart: A Multi-Staged Chart Generator from Natural Language Text","created":"2021-04-09","cited_by_count":5},{"id":"2506.01511","title":"Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment","created":"2025-06-02","cited_by_count":3},{"id":"2506.06175","title":"Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach","created":"2025-06-06","cited_by_count":1}],"next_cursor":null}