{"list":"other","total":78,"rows":[{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"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":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"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":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"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":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141},{"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":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99},{"id":"2503.07314","title":"Automated Movie Generation via Multi-Agent CoT Planning","created":"2025-03-10","cited_by_count":89},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77},{"id":"2411.16375","title":"Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing","created":"2024-11-25","cited_by_count":74},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2506.09027","title":"Diffuse and Disperse: Image Generation with Representation Regularization","created":"2025-06-10","cited_by_count":70},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2501.04698","title":"ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning","created":"2025-01-08","cited_by_count":68},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64},{"id":"2211.14575","title":"Efficient Video Prediction via Sparsely Conditioned Flow Matching","created":"2022-11-26","cited_by_count":55},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36},{"id":"2503.16153","title":"FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing","created":"2025-03-20","cited_by_count":22},{"id":"2504.09656","title":"KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation","created":"2025-04-13","cited_by_count":8}],"next_cursor":null}