{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"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":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"2012.03912","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","created":"2020-12-07","cited_by_count":95},{"id":"2210.07506","title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","created":"2022-10-14","cited_by_count":86},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2012.09812","title":"ViNG: Learning Open-World Navigation with Visual Goals","created":"2020-12-17","cited_by_count":80},{"id":"2007.14626","title":"Object-and-Action Aware Model for Visual Language Navigation","created":"2020-07-29","cited_by_count":77},{"id":"2007.11018","title":"Learning Object Relation Graph and Tentative Policy for Visual Navigation","created":"2020-07-21","cited_by_count":64},{"id":"1906.00347","title":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","created":"2019-06-02","cited_by_count":55},{"id":"2211.16649","title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation","created":"2022-11-30","cited_by_count":55},{"id":"2105.09447","title":"VTNet: Visual Transformer Network for Object Goal Navigation","created":"2021-05-20","cited_by_count":51},{"id":"1908.03409","title":"Transferable Representation Learning in Vision-and-Language Navigation","created":"2019-08-09","cited_by_count":48},{"id":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48},{"id":"2206.07423","title":"Zero-shot object goal visual navigation","created":"2022-06-15","cited_by_count":31},{"id":"2211.11116","title":"Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation","created":"2022-11-20","cited_by_count":9},{"id":"2304.10773","title":"Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation","created":"2023-04-21","cited_by_count":9},{"id":"2208.13031","title":"Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigation","created":"2022-08-27","cited_by_count":3}],"next_cursor":null}