{"list":"other","total":129,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"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":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2506.21539","title":"WorldVLA: Towards Autoregressive Action World Model","created":"2025-06-26","cited_by_count":367},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182},{"id":"2505.12705","title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","created":"2025-05-19","cited_by_count":179},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2412.15109","title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation","created":"2024-12-19","cited_by_count":161},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2310.09615","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","created":"2023-10-14","cited_by_count":89},{"id":"1704.05831","title":"Learning to Generate Long-term Future via Hierarchical Prediction","created":"2017-04-19","cited_by_count":88},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75},{"id":"2010.02054","title":"Improving Generative Imagination in Object-Centric World Models","created":"2020-10-05","cited_by_count":71},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69},{"id":"2003.04035","title":"Transformation-based Adversarial Video Prediction on Large-Scale Data","created":"2020-03-09","cited_by_count":66},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61},{"id":"2211.14575","title":"Efficient Video Prediction via Sparsely Conditioned Flow Matching","created":"2022-11-26","cited_by_count":55},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44},{"id":"1910.02425","title":"Structured Object-Aware Physics Prediction for Video Modeling and Planning","created":"2019-10-06","cited_by_count":43},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37},{"id":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"2406.19320","title":"Efficient World Models with Context-Aware Tokenization","created":"2024-06-27","cited_by_count":33},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29},{"id":"2006.07034","title":"Benchmarking Unsupervised Object Representations for Video Sequences","created":"2020-06-12","cited_by_count":27},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27}],"next_cursor":"100"}