{"list":"other","total":53,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2305.07015","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","created":"2023-05-11","cited_by_count":489},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2403.04692","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","created":"2024-03-07","cited_by_count":329},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2311.16518","title":"SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution","created":"2023-11-27","cited_by_count":315},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"2312.06640","title":"Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution","created":"2023-12-11","cited_by_count":132},{"id":"2406.18583","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","created":"2024-06-05","cited_by_count":132},{"id":"2310.07702","title":"ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models","created":"2023-10-11","cited_by_count":128},{"id":"2411.10958","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","created":"2024-11-17","cited_by_count":114},{"id":"2311.16973","title":"DemoFusion: Democratising High-Resolution Image Generation With No $$$","created":"2023-11-24","cited_by_count":107},{"id":"2412.15205","title":"FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching","created":"2024-12-19","cited_by_count":80},{"id":"2502.20388","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","created":"2025-02-27","cited_by_count":71},{"id":"2407.02158","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","created":"2024-07-02","cited_by_count":65},{"id":"2407.07667","title":"VEnhancer: Generative Space-Time Enhancement for Video Generation","created":"2024-07-10","cited_by_count":64},{"id":"2501.01320","title":"SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration","created":"2025-01-02","cited_by_count":62},{"id":"2501.08453","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","created":"2025-01-14","cited_by_count":60},{"id":"2406.07255","title":"Towards Realistic Data Generation for Real-World Super-Resolution","created":"2024-06-11","cited_by_count":56},{"id":"2410.08261","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","created":"2024-10-10","cited_by_count":56},{"id":"2501.02976","title":"STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution","created":"2025-01-06","cited_by_count":56},{"id":"2402.10491","title":"Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation","created":"2024-02-16","cited_by_count":51},{"id":"2503.06617","title":"Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling","created":"2025-03-09","cited_by_count":48},{"id":"2409.02097","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","created":"2024-09-03","cited_by_count":43},{"id":"2503.14908","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation","created":"2025-03-19","cited_by_count":36},{"id":"2412.16112","title":"CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up","created":"2024-12-20","cited_by_count":28},{"id":"2107.13812","title":"From Continuity to Editability: Inverting GANs with Consecutive Images","created":"2021-07-29","cited_by_count":25},{"id":"2403.02084","title":"ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models","created":"2024-03-04","cited_by_count":23},{"id":"2303.09757","title":"Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior","created":"2023-03-17","cited_by_count":22},{"id":"2403.02601","title":"Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning","created":"2024-03-05","cited_by_count":19},{"id":"2412.00878","title":"Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration","created":"2024-12-01","cited_by_count":17},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16},{"id":"2409.02919","title":"HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts","created":"2024-09-04","cited_by_count":15},{"id":"2308.06097","title":"RIGID: Recurrent GAN Inversion and Editing of Real Face Videos","created":"2023-08-11","cited_by_count":13},{"id":"2502.12640","title":"RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation","created":"2025-02-18","cited_by_count":9}],"next_cursor":null}