{"list":"other","total":69,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"2205.09743","title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","created":"2022-05-19","cited_by_count":191},{"id":"2305.10430","title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","created":"2023-05-17","cited_by_count":191},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2203.11934","title":"Learning from All Vehicles","created":"2022-03-22","cited_by_count":135},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1610.00527","title":"Video Pixel Networks","created":"2016-10-03","cited_by_count":108},{"id":"2002.09219","title":"Stochastic Latent Residual Video Prediction","created":"2020-02-21","cited_by_count":108},{"id":"2308.01661","title":"BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout","created":"2023-08-03","cited_by_count":102},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101},{"id":"1412.6604","title":"Video (language) modeling: a baseline for generative models of natural videos","created":"2014-12-20","cited_by_count":92},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2309.00610","title":"CityDreamer: Compositional Generative Model of Unbounded 3D Cities","created":"2023-09-01","cited_by_count":76},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68},{"id":"2205.13817","title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models","created":"2022-05-27","cited_by_count":53},{"id":"2212.08914","title":"Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark","created":"2022-12-17","cited_by_count":26}],"next_cursor":null}