{"list":"other","total":61,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"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":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"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":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"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":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2103.14127","title":"Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes","created":"2021-03-25","cited_by_count":218},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2403.03174","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","created":"2024-03-05","cited_by_count":129},{"id":"1804.05172","title":"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach","created":"2018-04-14","cited_by_count":120},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2304.05501","title":"L3MVN: Leveraging Large Language Models for Visual Target Navigation","created":"2023-04-11","cited_by_count":120},{"id":"2011.09584","title":"ACRONYM: A Large-Scale Grasp Dataset Based on Simulation","created":"2020-11-18","cited_by_count":117},{"id":"2305.11176","title":"Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model","created":"2023-05-18","cited_by_count":116},{"id":"2101.01132","title":"Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter","created":"2021-01-04","cited_by_count":95},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"2007.08073","title":"Unseen Object Instance Segmentation for Robotic Environments","created":"2020-07-16","cited_by_count":85},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82},{"id":"1912.03628","title":"6-DOF Grasping for Target-driven Object Manipulation in Clutter","created":"2019-12-08","cited_by_count":70},{"id":"1909.04810","title":"Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network","created":"2019-09-11","cited_by_count":59},{"id":"1902.01626","title":"EasyLabel: A Semi-Automatic Pixel-wise Object Annotation Tool for Creating Robotic RGB-D Datasets","created":"2019-02-05","cited_by_count":58},{"id":"2205.15509","title":"ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts","created":"2022-05-31","cited_by_count":45},{"id":"2107.05287","title":"End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB","created":"2021-07-12","cited_by_count":44},{"id":"2308.00640","title":"VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes","created":"2023-08-01","cited_by_count":42},{"id":"2307.13204","title":"GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Grasping","created":"2023-07-25","cited_by_count":40},{"id":"2312.01421","title":"RobotGPT: Robot Manipulation Learning from ChatGPT","created":"2023-12-03","cited_by_count":39},{"id":"2011.06431","title":"Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping","created":"2020-11-12","cited_by_count":27},{"id":"2406.09489","title":"Language-driven Grasp Detection","created":"2024-06-13","cited_by_count":26},{"id":"1906.09836","title":"Learning Grasp Affordance Reasoning through Semantic Relations","created":"2019-06-24","cited_by_count":23},{"id":"2311.05779","title":"Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter","created":"2023-11-09","cited_by_count":22},{"id":"2210.01287","title":"Robot Task Planning and Situation Handling in Open Worlds","created":"2022-10-04","cited_by_count":10},{"id":"2302.07824","title":"Instance-wise Grasp Synthesis for Robotic Grasping","created":"2023-02-15","cited_by_count":5}],"next_cursor":null}