{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"2312.13139","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","created":"2023-12-20","cited_by_count":364},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"1807.06158","title":"Generative Adversarial Imitation from Observation","created":"2018-07-17","cited_by_count":184},{"id":"2001.02908","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","created":"2020-01-09","cited_by_count":180},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","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":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"2401.09985","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","created":"2024-01-18","cited_by_count":89},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"2011.06507","title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","created":"2020-11-12","cited_by_count":82},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"id":"2212.00235","title":"VIDM: Video Implicit Diffusion Models","created":"2022-12-01","cited_by_count":78},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78},{"id":"1911.09676","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","created":"2019-11-21","cited_by_count":73},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68},{"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":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44},{"id":"1910.11670","title":"Contextual Imagined Goals for Self-Supervised Robotic Learning","created":"2019-10-23","cited_by_count":40},{"id":"2204.02393","title":"Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining","created":"2022-04-05","cited_by_count":37},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35},{"id":"2309.13041","title":"Robotic Offline RL from Internet Videos via Value-Function Pre-Training","created":"2023-09-22","cited_by_count":33},{"id":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28},{"id":"1905.09335","title":"Imitation Learning from Video by Leveraging Proprioception","created":"2019-05-22","cited_by_count":23},{"id":"2403.05304","title":"Spatiotemporal Predictive Pre-training for Robotic Motor Control","created":"2024-03-08","cited_by_count":22},{"id":"2306.12860","title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","created":"2023-06-22","cited_by_count":14},{"id":"2203.10528","title":"Stochastic Video Prediction with Structure and Motion","created":"2022-03-20","cited_by_count":8},{"id":"2204.12458","title":"Learning Value Functions from Undirected State-only Experience","created":"2022-04-26","cited_by_count":8},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8}],"next_cursor":null}