{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2310.14189","title":"Improved Techniques for Training Consistency Models","created":"2023-10-22","cited_by_count":439},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"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":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"1904.03626","title":"On The Power of Curriculum Learning in Training Deep Networks","created":"2019-04-07","cited_by_count":286},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2009.09941","title":"PP-OCR: A Practical Ultra Lightweight OCR System","created":"2020-09-21","cited_by_count":151},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101},{"id":"2307.06940","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","created":"2023-07-13","cited_by_count":90},{"id":"2312.16693","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","created":"2023-12-27","cited_by_count":70},{"id":"1412.1353","title":"Curriculum Learning of Multiple Tasks","created":"2014-12-03","cited_by_count":66},{"id":"2402.14780","title":"Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models","created":"2024-02-22","cited_by_count":55},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32},{"id":"2403.10348","title":"Denoising Task Difficulty-based Curriculum for Training Diffusion Models","created":"2024-03-15","cited_by_count":27},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24},{"id":"2003.04679","title":"Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog","created":"2020-03-10","cited_by_count":13},{"id":"2109.01839","title":"Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark","created":"2021-09-04","cited_by_count":12},{"id":"2306.06870","title":"Sticker820K: Empowering Interactive Retrieval with Stickers","created":"2023-06-12","cited_by_count":6},{"id":"2405.03958","title":"Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model","created":"2024-05-07","cited_by_count":6},{"id":"2412.08259","title":"VSD2M: A Large-scale Vision-language Sticker Dataset for Multi-frame Animated Sticker Generation","created":"2024-12-11","cited_by_count":4},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3},{"id":"2402.06088","title":"Animated Stickers: Bringing Stickers to Life with Video Diffusion","created":"2024-02-08","cited_by_count":3}],"next_cursor":null}