{"total":62,"rows":[{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622,"area":null},{"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,"area":null},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551,"area":null},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523,"area":"wm"},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371,"area":null},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2204.06252","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","created":"2022-04-13","cited_by_count":138,"area":"offlinerl"},{"id":"2210.01911","title":"Grounding Language with Visual Affordances over Unstructured Data","created":"2022-10-04","cited_by_count":101,"area":null},{"id":"2303.03480","title":"Can an Embodied Agent Find Your \"Cat-shaped Mug\"? LLM-Guided Exploration for Zero-Shot Object Navigation","created":"2023-03-06","cited_by_count":74,"area":"agents"},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"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,"area":"vla"},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32,"area":null},{"id":"2311.00967","title":"Vision-Language Interpreter for Robot Task Planning","created":"2023-11-02","cited_by_count":30,"area":null},{"id":"2104.00492","title":"A Joint Network for Grasp Detection Conditioned on Natural Language Commands","created":"2021-04-01","cited_by_count":23,"area":null},{"id":"2311.05779","title":"Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter","created":"2023-11-09","cited_by_count":22,"area":null},{"id":"2111.07975","title":"Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement","created":"2021-11-15","cited_by_count":21,"area":null},{"id":"2102.08094","title":"Composing Pick-and-Place Tasks By Grounding Language","created":"2021-02-16","cited_by_count":20,"area":null},{"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,"area":null},{"id":"2410.07540","title":"CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection","created":"2024-10-10","cited_by_count":15,"area":"mllm"},{"id":"2303.05674","title":"Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors","created":"2023-03-10","cited_by_count":12,"area":"mllm"},{"id":"2212.07398","title":"Policy Adaptation from Foundation Model Feedback","created":"2022-12-14","cited_by_count":10,"area":"mllm"},{"id":"2402.01183","title":"LINGO-Space: Language-Conditioned Incremental Grounding for Space","created":"2024-02-02","cited_by_count":8,"area":null},{"id":"2107.00811","title":"Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2111.11099","title":"Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2307.08597","title":"Multimodal Diffusion Segmentation Model for Object Segmentation from Manipulation Instructions","created":"2023-07-17","cited_by_count":7,"area":null},{"id":"2201.01901","title":"Incremental Object Grounding Using Scene Graphs","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2311.04192","title":"JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2409.20548","title":"Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2207.14205","title":"DoRO: Disambiguation of referred object for embodied agents","created":"2022-07-28","cited_by_count":5,"area":null},{"id":"2307.07166","title":"Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks","created":"2023-07-14","cited_by_count":5,"area":null},{"id":"2312.15844","title":"Learning-To-Rank Approach for Identifying Everyday Objects Using a Physical-World Search Engine","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2502.03450","title":"Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System","created":"2025-02-05","cited_by_count":5,"area":"lr"},{"id":"2107.00789","title":"Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions","created":"2021-07-02","cited_by_count":4,"area":null},{"id":"2201.06317","title":"Language Model-Based Paired Variational Autoencoders for Robotic Language Learning","created":"2022-01-17","cited_by_count":4,"area":null},{"id":"2205.04026","title":"I Know What You Draw: Learning Grasp Detection Conditioned on a Few Freehand Sketches","created":"2022-05-09","cited_by_count":4,"area":null},{"id":"2307.05963","title":"GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation","created":"2023-07-12","cited_by_count":4,"area":null},{"id":"2207.03682","title":"Music-driven Dance Regeneration with Controllable Key Pose Constraints","created":"2022-07-08","cited_by_count":3,"area":null},{"id":"2307.04195","title":"Natural Language Instructions for Intuitive Human Interaction with Robotic Assistants in Field Construction Work","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2408.07910","title":"DM2RM: Dual-Mode Multimodal Ranking for Target Objects and Receptacles Based on Open-Vocabulary Instructions","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2410.00436","title":"Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2412.02140","title":"SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Images","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2106.08574","title":"Unsupervised Lexical Acquisition of Relative Spatial Concepts Using Spoken User Utterances","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2108.12536","title":"DASH: Modularized Human Manipulation Simulation with Vision and Language for Embodied AI","created":"2021-08-28","cited_by_count":2,"area":null},{"id":"2205.12089","title":"Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2309.07759","title":"PROGrasp: Pragmatic Human-Robot Communication for Object Grasping","created":"2023-09-14","cited_by_count":2,"area":null},{"id":"2310.12147","title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2503.17703","title":"RAIDER: Tool-Equipped Large Language Model Agent for Robotic Action Issue Detection, Explanation and Recovery","created":"2025-03-22","cited_by_count":2,"area":"agents"},{"id":"2107.14593","title":"Neural Variational Learning for Grounded Language Acquisition","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2110.10206","title":"Evaluating and Improving Interactions with Hazy Oracles","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2207.07437","title":"Learning Flexible Translation between Robot Actions and Language Descriptions","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2210.00858","title":"Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach","created":"2022-10-03","cited_by_count":1,"area":"lr"},{"id":"2303.02871","title":"Naming Objects for Vision-and-Language Manipulation","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2307.05942","title":"Prototypical Contrastive Transfer Learning for Multimodal Language Understanding","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2312.07451","title":"Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model","created":"2023-12-12","cited_by_count":1,"area":"mllm"},{"id":"2407.00985","title":"Object Segmentation from Open-Vocabulary Manipulation Instructions Based on Optimal Transport Polygon Matching with Multimodal Foundation Models","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2602.13126","title":"Automating UI Optimization through Multi-Agentic Reasoning","created":"2026-02-13","cited_by_count":1,"area":"agents"},{"id":"2301.03353","title":"Learning Bidirectional Action-Language Translation with Limited Supervision and Incongruent Input","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2310.12547","title":"PGA: Personalizing Grasping Agents with Single Human-Robot Interaction","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2503.23105","title":"Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2508.11759","title":"Using Natural Language for Human-Robot Collaboration in the Real World","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2608.10330","title":"Hierarchical Compositionality for An Assistive AI Agent","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2610.19723","title":"Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}