{"list":"other","total":63,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"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":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"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":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"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":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2402.11502","title":"GenAD: Generative End-to-End Autonomous Driving","created":"2024-02-18","cited_by_count":225},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191},{"id":"2210.17366","title":"Guided Conditional Diffusion for Controllable Traffic Simulation","created":"2022-10-31","cited_by_count":190},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126},{"id":"2306.06344","title":"Language-Guided Traffic Simulation via Scene-Level Diffusion","created":"2023-06-10","cited_by_count":111},{"id":"2210.06609","title":"TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios","created":"2022-10-12","cited_by_count":106},{"id":"2311.01017","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","created":"2023-11-02","cited_by_count":106},{"id":"2311.13549","title":"ADriver-I: A General World Model for Autonomous Driving","created":"2023-11-22","cited_by_count":104},{"id":"2306.06955","title":"A Brief Review of Hypernetworks in Deep Learning","created":"2023-06-12","cited_by_count":102},{"id":"2312.17655","title":"Visual Point Cloud Forecasting enables Scalable Autonomous Driving","created":"2023-12-29","cited_by_count":99},{"id":"2312.02934","title":"WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation","created":"2023-12-05","cited_by_count":93},{"id":"2405.04390","title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","created":"2024-05-07","cited_by_count":93},{"id":"2307.07947","title":"Language Conditioned Traffic Generation","created":"2023-07-16","cited_by_count":87},{"id":"2310.07771","title":"DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model","created":"2023-10-11","cited_by_count":75},{"id":"1612.03801","title":"DeepMind Lab","created":"2016-12-12","cited_by_count":74},{"id":"2303.04116","title":"TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction","created":"2023-03-07","cited_by_count":56},{"id":"2404.02903","title":"LidarDM: Generative LiDAR Simulation in a Generated World","created":"2024-04-03","cited_by_count":54},{"id":"2308.07234","title":"UniWorld: Autonomous Driving Pre-training via World Models","created":"2023-08-14","cited_by_count":33},{"id":"2311.11762","title":"MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations","created":"2023-11-20","cited_by_count":33},{"id":"2305.00813","title":"Neurosymbolic AI -- Why, What, and How","created":"2023-05-01","cited_by_count":19},{"id":"2306.01828","title":"Unifying (Machine) Vision via Counterfactual World Modeling","created":"2023-06-02","cited_by_count":19},{"id":"2203.12117","title":"NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty","created":"2022-03-23","cited_by_count":14},{"id":"2301.06294","title":"Neuro-Symbolic World Models for Adapting to Open World Novelty","created":"2023-01-16","cited_by_count":14},{"id":"2407.06083","title":"A Survey of Controllable Learning: Methods and Applications in Information Retrieval","created":"2024-07-04","cited_by_count":12},{"id":"2402.15989","title":"PIDformer: Transformer Meets Control Theory","created":"2024-02-25","cited_by_count":11},{"id":"2405.16914","title":"Rigorous Simulation-based Testing for Autonomous Driving Systems -- Targeting the Achilles' Heel of Four Open Autopilots","created":"2024-05-27","cited_by_count":2}],"next_cursor":null}