{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2312.02696","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","created":"2023-12-05","cited_by_count":402},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"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":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2301.04856","title":"Multimodal Deep Learning","created":"2023-01-12","cited_by_count":258},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2302.07685","title":"Video Probabilistic Diffusion Models in Projected Latent Space","created":"2023-02-15","cited_by_count":171},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"1511.02251","title":"Learning Visual Features from Large Weakly Supervised Data","created":"2015-11-06","cited_by_count":165},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"1911.09291","title":"Scalable methods for computing state similarity in deterministic Markov Decision Processes","created":"2019-11-21","cited_by_count":133},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2309.14320","title":"MUTEX: Learning Unified Policies from Multimodal Task Specifications","created":"2023-09-25","cited_by_count":70},{"id":"1812.02246","title":"Photo Wake-Up: 3D Character Animation from a Single Photo","created":"2018-12-05","cited_by_count":60},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"2305.17110","title":"IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality","created":"2023-05-26","cited_by_count":53},{"id":"2111.06387","title":"Learning Signal-Agnostic Manifolds of Neural Fields","created":"2021-11-11","cited_by_count":45},{"id":"2204.13060","title":"Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning","created":"2022-04-27","cited_by_count":38},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18},{"id":"2308.11198","title":"Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views","created":"2023-08-22","cited_by_count":16},{"id":"2104.02687","title":"Strumming to the Beat: Audio-Conditioned Contrastive Video Textures","created":"2021-04-06","cited_by_count":14},{"id":"1807.09245","title":"Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks","created":"2018-07-24","cited_by_count":11},{"id":"1711.03321","title":"A Separation Principle for Control in the Age of Deep Learning","created":"2017-11-09","cited_by_count":9},{"id":"2211.02201","title":"Learning Tool Morphology for Contact-Rich Manipulation Tasks with Differentiable Simulation","created":"2022-11-04","cited_by_count":9}],"next_cursor":null}