{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"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":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2310.07896","title":"NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration","created":"2023-10-11","cited_by_count":248},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","cited_by_count":121},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83},{"id":"1803.07616","title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","created":"2018-03-20","cited_by_count":73},{"id":"2412.04445","title":"Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos","created":"2024-12-05","cited_by_count":69},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58},{"id":"1703.07684","title":"Predicting Deeper into the Future of Semantic Segmentation","created":"2017-03-22","cited_by_count":51},{"id":"2510.18135","title":"World-in-World: World Models in a Closed-Loop World","created":"2025-10-20","cited_by_count":47},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44},{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44},{"id":"2512.24497","title":"What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?","created":"2025-12-30","cited_by_count":43},{"id":"2505.04999","title":"CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations","created":"2025-05-08","cited_by_count":41},{"id":"2505.17006","title":"CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning","created":"2025-05-22","cited_by_count":40},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29},{"id":"1806.09655","title":"Learning what you can do before doing anything","created":"2018-06-25","cited_by_count":26},{"id":"2412.10925","title":"Video Representation Learning with Joint-Embedding Predictive Architectures","created":"2024-12-14","cited_by_count":15},{"id":"2412.09551","title":"Video Creation by Demonstration","created":"2024-12-12","cited_by_count":8}],"next_cursor":null}