{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2401.13178","title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","created":"2024-01-24","cited_by_count":339},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2110.00534","title":"TEACh: Task-driven Embodied Agents that Chat","created":"2021-10-01","cited_by_count":197},{"id":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68},{"id":"1809.03470","title":"ViZDoom Competitions: Playing Doom from Pixels","created":"2018-09-10","cited_by_count":51},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43},{"id":"1705.04350","title":"Imagination improves Multimodal Translation","created":"2017-05-11","cited_by_count":38},{"id":"2405.15143","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","created":"2024-05-24","cited_by_count":33},{"id":"2211.10869","title":"UniMASK: Unified Inference in Sequential Decision Problems","created":"2022-11-20","cited_by_count":24},{"id":"2402.01695","title":"Language-Guided World Models: A Model-Based Approach to AI Control","created":"2024-01-24","cited_by_count":12},{"id":"2210.04443","title":"Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue","created":"2022-10-10","cited_by_count":10},{"id":"2407.03967","title":"Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks","created":"2024-07-04","cited_by_count":8},{"id":"2409.15922","title":"The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards","created":"2024-09-24","cited_by_count":7},{"id":"2410.24218","title":"Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use","created":"2024-10-31","cited_by_count":7},{"id":"2011.02917","title":"Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games","created":"2020-11-05","cited_by_count":3},{"id":"2409.14247","title":"Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language Models","created":"2024-09-21","cited_by_count":3},{"id":"2312.04736","title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning","created":"2023-12-07","cited_by_count":2}],"next_cursor":null}