{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","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":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141},{"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":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1309.2660","title":"Data-Driven Grasp Synthesis - A Survey","created":"2013-09-10","cited_by_count":106},{"id":"2403.14520","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","created":"2024-03-21","cited_by_count":97},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"id":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"1412.3128","title":"Real-Time Grasp Detection Using Convolutional Neural Networks","created":"2014-12-09","cited_by_count":76},{"id":"2404.04256","title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","created":"2024-04-05","cited_by_count":71},{"id":"1712.02036","title":"Learning Semantic Concepts and Order for Image and Sentence Matching","created":"2017-12-06","cited_by_count":62},{"id":"1909.04810","title":"Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network","created":"2019-09-11","cited_by_count":59},{"id":"2404.14966","title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","created":"2024-04-23","cited_by_count":57},{"id":"2109.09163","title":"CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation","created":"2021-09-19","cited_by_count":49},{"id":"2406.11142","title":"Graspness Discovery in Clutters for Fast and Accurate Grasp Detection","created":"2024-06-17","cited_by_count":48},{"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":"1611.05588","title":"Instance-aware Image and Sentence Matching with Selective Multimodal LSTM","created":"2016-11-17","cited_by_count":43},{"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":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41},{"id":"2311.00926","title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","created":"2023-11-02","cited_by_count":41},{"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":"2003.09644","title":"PointNet++ Grasping: Learning An End-to-end Spatial Grasp Generation Algorithm from Sparse Point Clouds","created":"2020-03-21","cited_by_count":39},{"id":"2404.01705","title":"Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model","created":"2024-04-02","cited_by_count":37},{"id":"2404.08406","title":"MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion","created":"2024-04-12","cited_by_count":35},{"id":"2302.12610","title":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","created":"2023-02-24","cited_by_count":34},{"id":"2309.09818","title":"Grasp-Anything: Large-scale Grasp Dataset from Foundation Models","created":"2023-09-18","cited_by_count":33},{"id":"2404.02457","title":"RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic Segmentation","created":"2024-04-03","cited_by_count":33},{"id":"2405.18014","title":"Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model","created":"2024-05-28","cited_by_count":31},{"id":"1803.02209","title":"Fully Convolutional Grasp Detection Network with Oriented Anchor Box","created":"2018-03-06","cited_by_count":27},{"id":"2405.15463","title":"PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis","created":"2024-05-24","cited_by_count":26},{"id":"2406.09489","title":"Language-driven Grasp Detection","created":"2024-06-13","cited_by_count":26},{"id":"2402.15761","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","created":"2024-02-24","cited_by_count":22},{"id":"2402.06798","title":"Reasoning Grasping via Multimodal Large Language Model","created":"2024-02-09","cited_by_count":20},{"id":"2203.08037","title":"Interactive Robotic Grasping with Attribute-Guided Disambiguation","created":"2022-03-15","cited_by_count":19},{"id":"2205.04028","title":"Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions","created":"2022-05-09","cited_by_count":19},{"id":"2310.05239","title":"Lan-grasp: Using Large Language Models for Semantic Object Grasping and Placement","created":"2023-10-08","cited_by_count":16},{"id":"2407.13842","title":"Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidance","created":"2024-07-18","cited_by_count":16},{"id":"2409.12521","title":"GraspSAM: When Segment Anything Model Meets Grasp Detection","created":"2024-09-19","cited_by_count":13},{"id":"2406.08234","title":"MaIL: Improving Imitation Learning with Mamba","created":"2024-06-12","cited_by_count":11},{"id":"2407.19832","title":"ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2","created":"2024-07-29","cited_by_count":10},{"id":"2211.04275","title":"Machine Learning-based Framework for Optimally Solving the Analytical Inverse Kinematics for Redundant Manipulators","created":"2022-11-08","cited_by_count":9},{"id":"2407.17967","title":"Lightweight Language-driven Grasp Detection using Conditional Consistency Model","created":"2024-07-25","cited_by_count":9},{"id":"2211.02516","title":"Singularity Avoidance with Application to Online Trajectory Optimization for Serial Manipulators","created":"2022-11-04","cited_by_count":7},{"id":"2409.10419","title":"HiFi-CS: Towards Open Vocabulary Visual Grounding For Robotic Grasping Using Vision-Language Models","created":"2024-09-16","cited_by_count":7},{"id":"2407.19877","title":"Language-driven Grasp Detection with Mask-guided Attention","created":"2024-07-29","cited_by_count":2}],"next_cursor":null}