{"total":42,"rows":[{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2506.02161","title":"TIIF-Bench: How Does Your T2I Model Follow Your Instructions?","created":"2025-06-02","cited_by_count":69,"area":null},{"id":"2506.03147","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","created":"2025-06-03","cited_by_count":66,"area":null},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49,"area":null},{"id":"2507.06119","title":"Omni-Video: Democratizing Unified Video Understanding and Generation","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2411.06558","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","created":"2024-11-10","cited_by_count":37,"area":null},{"id":"2503.14908","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation","created":"2025-03-19","cited_by_count":36,"area":null},{"id":"2412.01819","title":"Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis","created":"2024-12-02","cited_by_count":33,"area":null},{"id":"2412.18653","title":"1.58-bit FLUX","created":"2024-12-24","cited_by_count":31,"area":null},{"id":"2503.12885","title":"DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models","created":"2025-03-17","cited_by_count":28,"area":null},{"id":"2510.20661","title":"UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset","created":"2025-10-23","cited_by_count":18,"area":null},{"id":"2512.05150","title":"TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows","created":"2025-12-03","cited_by_count":17,"area":null},{"id":"2501.09503","title":"AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation","created":"2025-01-16","cited_by_count":16,"area":null},{"id":"2508.06125","title":"SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning","created":"2025-08-08","cited_by_count":16,"area":null},{"id":"2503.14503","title":"The Power of Context: How Multimodality Improves Image Super-Resolution","created":"2025-03-18","cited_by_count":15,"area":null},{"id":"2503.21749","title":"LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis","created":"2025-03-27","cited_by_count":15,"area":null},{"id":"2511.06876","title":"Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions","created":"2025-11-10","cited_by_count":14,"area":null},{"id":"2504.20996","title":"X-Fusion: Introducing New Modality to Frozen Large Language Models","created":"2025-04-29","cited_by_count":13,"area":null},{"id":"2507.04947","title":"DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2504.06982","title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","created":"2025-04-09","cited_by_count":12,"area":null},{"id":"2508.06080","title":"DreamVE: Unified Instruction-based Image and Video Editing","created":"2025-08-08","cited_by_count":11,"area":null},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2506.08210","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2505.23484","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2504.19724","title":"RepText: Rendering Visual Text via Replicating","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2603.11593","title":"WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2409.19946","title":"Illustrious: an Open Advanced Illustration Model","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2506.16679","title":"How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions","created":"2025-06-20","cited_by_count":5,"area":null},{"id":"2510.04201","title":"World-To-Image: Grounding Text-to-Image Generation with Agent-Driven World Knowledge","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2602.19497","title":"MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2505.15172","title":"Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2602.20672","title":"BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2604.12322","title":"Self-Adversarial One Step Generation via Condition Shifting","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2604.18168","title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2506.23347","title":"CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2602.22734","title":"Asymmetric Idiosyncrasies in Multimodal Models","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.24965","title":"Self-Corrected Image Generation with Explainable Latent Rewards","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.20147","title":"PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2603.26866","title":"LACON: Training Text-to-Image Model from Uncurated Data","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.24021","title":"Token-to-Token Alignment of Text Embeddings for Semantic Blending","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}