{"list":"other","total":65,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"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":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"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":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"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":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"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":"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":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"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":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","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":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220},{"id":"2303.12346","title":"NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation","created":"2023-03-22","cited_by_count":171},{"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":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154},{"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":"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":"2311.02848","title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","created":"2023-11-06","cited_by_count":125},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2312.02139","title":"DiffiT: Diffusion Vision Transformers for Image Generation","created":"2023-12-04","cited_by_count":106},{"id":"2403.14939","title":"STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians","created":"2024-03-22","cited_by_count":102},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50},{"id":"2311.10242","title":"Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers","created":"2023-11-17","cited_by_count":36},{"id":"2411.10836","title":"AnimateAnything: Consistent and Controllable Animation for Video Generation","created":"2024-11-16","cited_by_count":35},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25},{"id":"2404.02148","title":"Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models","created":"2024-04-02","cited_by_count":24},{"id":"2106.10528","title":"Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net","created":"2021-06-19","cited_by_count":22},{"id":"2410.10802","title":"Boosting Camera Motion Control for Video Diffusion Transformers","created":"2024-10-14","cited_by_count":20},{"id":"2412.07721","title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","created":"2024-12-10","cited_by_count":18},{"id":"2403.02332","title":"UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control","created":"2024-03-04","cited_by_count":14},{"id":"2412.01316","title":"Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation","created":"2024-12-02","cited_by_count":12},{"id":"2412.01429","title":"CPA: Camera-pose-awareness Diffusion Transformer for Video Generation","created":"2024-12-02","cited_by_count":10}],"next_cursor":null}