{"list":"other","total":93,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"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":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"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":"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":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"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":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2307.14535","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","created":"2023-07-26","cited_by_count":159},{"id":"1810.10191","title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","created":"2018-10-24","cited_by_count":154},{"id":"1802.08705","title":"PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning","created":"2018-02-23","cited_by_count":150},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131},{"id":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","cited_by_count":121},{"id":"2304.05501","title":"L3MVN: Leveraging Large Language Models for Visual Target Navigation","created":"2023-04-11","cited_by_count":120},{"id":"2311.00899","title":"RoboVQA: Multimodal Long-Horizon Reasoning for Robotics","created":"2023-11-01","cited_by_count":120},{"id":"2306.06531","title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers","created":"2023-06-10","cited_by_count":113},{"id":"2309.11382","title":"Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions","created":"2023-09-20","cited_by_count":110},{"id":"1805.11085","title":"More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch","created":"2018-05-28","cited_by_count":102},{"id":"2407.12366","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","created":"2024-07-17","cited_by_count":98},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","cited_by_count":94},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2310.10103","title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","created":"2023-10-16","cited_by_count":89},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"1709.10489","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","created":"2017-09-29","cited_by_count":77},{"id":"2311.12015","title":"GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration","created":"2023-11-20","cited_by_count":77},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"2402.13232","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","created":"2024-02-20","cited_by_count":69},{"id":"2212.03858","title":"See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation","created":"2022-12-07","cited_by_count":68},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67},{"id":"2304.08448","title":"An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT","created":"2023-04-17","cited_by_count":57},{"id":"2111.14843","title":"Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds","created":"2021-11-29","cited_by_count":41},{"id":"2312.01421","title":"RobotGPT: Robot Manipulation Learning from ChatGPT","created":"2023-12-03","cited_by_count":39},{"id":"2406.19464","title":"ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data","created":"2024-06-27","cited_by_count":31},{"id":"2311.00967","title":"Vision-Language Interpreter for Robot Task Planning","created":"2023-11-02","cited_by_count":30},{"id":"2201.05247","title":"Multi-agent Motion Planning from Signal Temporal Logic Specifications","created":"2022-01-13","cited_by_count":21},{"id":"2207.10148","title":"Learning Deformable Object Manipulation from Expert Demonstrations","created":"2022-07-20","cited_by_count":19},{"id":"2209.05802","title":"Learning Agent-Aware Affordances for Closed-Loop Interaction with Articulated Objects","created":"2022-09-13","cited_by_count":16},{"id":"2308.03620","title":"Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods","created":"2023-08-07","cited_by_count":15},{"id":"2107.05842","title":"Motion Planning by Learning the Solution Manifold in Trajectory Optimization","created":"2021-07-13","cited_by_count":13},{"id":"2112.06374","title":"Learning Generalizable Vision-Tactile Robotic Grasping Strategy for Deformable Objects via Transformer","created":"2021-12-13","cited_by_count":13},{"id":"2210.01116","title":"That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulation","created":"2022-10-03","cited_by_count":12},{"id":"2212.04573","title":"Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation","created":"2022-12-08","cited_by_count":12},{"id":"2309.02754","title":"Pre- and post-contact policy decomposition for non-prehensile manipulation with zero-shot sim-to-real transfer","created":"2023-09-06","cited_by_count":12},{"id":"2101.02252","title":"Playing with Food: Learning Food Item Representations through Interactive Exploration","created":"2021-01-06","cited_by_count":8},{"id":"2204.13879","title":"DGBench: An Open-Source, Reproducible Benchmark for Dynamic Grasping","created":"2022-04-29","cited_by_count":5}],"next_cursor":null}