{"list":"other","total":66,"rows":[{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2310.20700","title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","created":"2023-10-31","cited_by_count":233},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2010.02824","title":"Support-set bottlenecks for video-text representation learning","created":"2020-10-06","cited_by_count":170},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123},{"id":"1811.09245","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","created":"2018-11-22","cited_by_count":120},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2307.14073","title":"VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet","created":"2023-07-26","cited_by_count":83},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70},{"id":"2410.21264","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","created":"2024-10-28","cited_by_count":46},{"id":"2412.07720","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","created":"2024-12-10","cited_by_count":45},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43},{"id":"2310.16656","title":"A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation","created":"2023-10-25","cited_by_count":41},{"id":"2403.16407","title":"A Survey on Long Video Generation: Challenges, Methods, and Prospects","created":"2024-03-25","cited_by_count":40},{"id":"1912.08860","title":"Lower Dimensional Kernels for Video Discriminators","created":"2019-12-18","cited_by_count":37},{"id":"2412.12095","title":"Causal Diffusion Transformers for Generative Modeling","created":"2024-12-16","cited_by_count":31},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30},{"id":"2111.11133","title":"L-Verse: Bidirectional Generation Between Image and Text","created":"2021-11-22","cited_by_count":15},{"id":"2404.18620","title":"FlexiFilm: Long Video Generation with Flexible Conditions","created":"2024-04-29","cited_by_count":13},{"id":"2503.06268","title":"Get In Video: Add Anything You Want to the Video","created":"2025-03-08","cited_by_count":12},{"id":"2502.07701","title":"Magic 1-For-1: Generating One Minute Video Clips within One Minute","created":"2025-02-11","cited_by_count":10},{"id":"2503.12077","title":"V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents","created":"2025-03-15","cited_by_count":9},{"id":"2503.01115","title":"WeGen: A Unified Model for Interactive Multimodal Generation as We Chat","created":"2025-03-03","cited_by_count":7}],"next_cursor":null}