{"list":"other","total":75,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"2310.10639","title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","created":"2023-10-16","cited_by_count":269},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2108.03272","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","created":"2021-08-06","cited_by_count":194},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160},{"id":"2012.02924","title":"iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes","created":"2020-12-05","cited_by_count":155},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"2310.05418","title":"Humanoid Agents: Platform for Simulating Human-like Generative Agents","created":"2023-10-09","cited_by_count":73},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"2407.10943","title":"GRUtopia: Dream General Robots in a City at Scale","created":"2024-07-15","cited_by_count":59},{"id":"2312.05208","title":"ControlRoom3D: Room Generation using Semantic Proxy Rooms","created":"2023-12-08","cited_by_count":56},{"id":"2007.04979","title":"A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks","created":"2020-07-09","cited_by_count":52},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45},{"id":"1903.00784","title":"Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents","created":"2019-03-02","cited_by_count":44},{"id":"2410.09604","title":"EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment","created":"2024-10-12","cited_by_count":42},{"id":"1801.07357","title":"CHALET: Cornell House Agent Learning Environment","created":"2018-01-23","cited_by_count":38},{"id":"2411.09823","title":"Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting","created":"2024-11-14","cited_by_count":38},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35},{"id":"2412.20977","title":"UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI","created":"2024-12-30","cited_by_count":25},{"id":"2009.04300","title":"SEAN: Social Environment for Autonomous Navigation","created":"2020-09-09","cited_by_count":18},{"id":"2403.19267","title":"MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs","created":"2024-03-28","cited_by_count":18},{"id":"2211.06318","title":"Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence","created":"2022-10-31","cited_by_count":16},{"id":"2306.00087","title":"Adaptive Coordination in Social Embodied Rearrangement","created":"2023-05-31","cited_by_count":14},{"id":"2312.03395","title":"Diffused Task-Agnostic Milestone Planner","created":"2023-12-06","cited_by_count":12},{"id":"2404.18243","title":"LEGENT: Open Platform for Embodied Agents","created":"2024-04-28","cited_by_count":12},{"id":"2409.12471","title":"Arena 4.0: A Comprehensive ROS2 Development and Benchmarking Platform for Human-centric Navigation Using Generative-Model-based Environment Generation","created":"2024-09-19","cited_by_count":4}],"next_cursor":null}