{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168},{"id":"2404.13686","title":"Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis","created":"2024-04-21","cited_by_count":156},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2002.12655","title":"A U-Net Based Discriminator for Generative Adversarial Networks","created":"2020-02-28","cited_by_count":128},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2104.03310","title":"Regularizing Generative Adversarial Networks under Limited Data","created":"2021-04-07","cited_by_count":107},{"id":"2503.10592","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models","created":"2025-03-13","cited_by_count":98},{"id":"2308.14749","title":"MagicEdit: High-Fidelity and Temporally Coherent Video Editing","created":"2023-08-28","cited_by_count":76},{"id":"2405.20279","title":"CV-VAE: A Compatible Video VAE for Latent Generative Video Models","created":"2024-05-30","cited_by_count":70},{"id":"2501.01320","title":"SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration","created":"2025-01-02","cited_by_count":62},{"id":"2411.17459","title":"WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model","created":"2024-11-26","cited_by_count":57},{"id":"2312.02928","title":"LivePhoto: Real Image Animation with Text-guided Motion Control","created":"2023-12-05","cited_by_count":44},{"id":"2410.08184","title":"Scaling Laws For Diffusion Transformers","created":"2024-10-10","cited_by_count":44},{"id":"2506.12103","title":"The Amazon Nova Family of Models: Technical Report and Model Card","created":"2025-03-17","cited_by_count":41},{"id":"2411.17470","title":"Towards Precise Scaling Laws for Video Diffusion Transformers","created":"2024-11-25","cited_by_count":20},{"id":"2501.06173","title":"VideoAuteur: Towards Long Narrative Video Generation","created":"2025-01-10","cited_by_count":18},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15}],"next_cursor":null}