{"list":"other","total":96,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2110.00534","title":"TEACh: Task-driven Embodied Agents that Chat","created":"2021-10-01","cited_by_count":197},{"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":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2204.03514","title":"Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale","created":"2022-04-07","cited_by_count":117},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"1812.00971","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","created":"2018-12-03","cited_by_count":93},{"id":"2001.09212","title":"PCGRL: Procedural Content Generation via Reinforcement Learning","created":"2020-01-24","cited_by_count":90},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2007.12868","title":"OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets","created":"2020-07-25","cited_by_count":74},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65},{"id":"1808.02084","title":"Deep Generative Modeling for Scene Synthesis via Hybrid Representations","created":"2018-08-06","cited_by_count":63},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"1907.11308","title":"SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation","created":"2019-07-25","cited_by_count":55},{"id":"2008.12760","title":"AllenAct: A Framework for Embodied AI Research","created":"2020-08-28","cited_by_count":54},{"id":"2205.03532","title":"Factory: Fast Contact for Robotic Assembly","created":"2022-05-07","cited_by_count":54},{"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":"1904.05879","title":"Two Body Problem: Collaborative Visual Task Completion","created":"2019-04-11","cited_by_count":45},{"id":"2105.14074","title":"Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning","created":"2021-05-28","cited_by_count":43},{"id":"2105.02993","title":"Learning Controllable Content Generators","created":"2021-05-06","cited_by_count":40},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39},{"id":"1505.06289","title":"Text to 3D Scene Generation with Rich Lexical Grounding","created":"2015-05-23","cited_by_count":36},{"id":"1902.03570","title":"EvalAI: Towards Better Evaluation Systems for AI Agents","created":"2019-02-10","cited_by_count":34},{"id":"2204.02960","title":"Simple and Effective Synthesis of Indoor 3D Scenes","created":"2022-04-06","cited_by_count":33},{"id":"2203.07359","title":"Stubborn: A Strong Baseline for Indoor Object Navigation","created":"2022-03-14","cited_by_count":32},{"id":"2010.08600","title":"Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning","created":"2020-10-16","cited_by_count":30},{"id":"2010.05190","title":"Learning Adaptive Language Interfaces through Decomposition","created":"2020-10-11","cited_by_count":22},{"id":"2202.00660","title":"Interactron: Embodied Adaptive Object Detection","created":"2022-02-01","cited_by_count":21},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20},{"id":"2110.09991","title":"Towards Optimal Correlational Object Search","created":"2021-10-19","cited_by_count":14},{"id":"2009.12395","title":"SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors","created":"2020-09-25","cited_by_count":11},{"id":"1703.00061","title":"SceneSuggest: Context-driven 3D Scene Design","created":"2017-02-28","cited_by_count":8},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7},{"id":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6},{"id":"2202.02418","title":"StandardSim: A Synthetic Dataset For Retail Environments","created":"2022-02-04","cited_by_count":6},{"id":"2203.08141","title":"Object Manipulation via Visual Target Localization","created":"2022-03-15","cited_by_count":6},{"id":"2101.02903","title":"Geometry-Based Layout Generation with Hyper-Relations AMONG Objects","created":"2021-01-08","cited_by_count":2},{"id":"2204.04867","title":"Structured Graph Variational Autoencoders for Indoor Furniture layout Generation","created":"2022-04-11","cited_by_count":1}],"next_cursor":null}