{"total":365,"rows":[{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071,"area":"mllm"},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484,"area":"vla"},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"area":null},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484,"area":null},{"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,"area":"agents"},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451,"area":"lr"},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415,"area":null},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346,"area":"wm"},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280,"area":"lr"},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196,"area":null},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190,"area":"lr"},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2406.04882","title":"InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment","created":"2024-06-07","cited_by_count":157,"area":null},{"id":"2412.06224","title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","created":"2024-12-09","cited_by_count":156,"area":"vla"},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135,"area":"agents"},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130,"area":null},{"id":"2307.12907","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","created":"2023-07-24","cited_by_count":124,"area":null},{"id":"2309.11382","title":"Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions","created":"2023-09-20","cited_by_count":110,"area":"wm"},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2311.16098","title":"On Bringing Robots Home","created":"2023-11-27","cited_by_count":101,"area":null},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91,"area":null},{"id":"2310.10103","title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","created":"2023-10-16","cited_by_count":89,"area":null},{"id":"2401.04334","title":"Large Language Models for Robotics: Opportunities, Challenges, and Perspectives","created":"2024-01-09","cited_by_count":89,"area":"mllm"},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2410.05273","title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","created":"2024-09-12","cited_by_count":75,"area":"mllm"},{"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":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2303.00855","title":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","created":"2023-03-01","cited_by_count":67,"area":"agents"},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67,"area":"wm"},{"id":"2404.01943","title":"Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation","created":"2024-04-02","cited_by_count":65,"area":null},{"id":"2506.17221","title":"VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning","created":"2025-06-20","cited_by_count":63,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56,"area":null},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55,"area":"agents"},{"id":"2310.03923","title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","created":"2023-10-05","cited_by_count":54,"area":null},{"id":"2405.17596","title":"GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane","created":"2024-05-27","cited_by_count":53,"area":null},{"id":"2404.00210","title":"VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models","created":"2024-03-30","cited_by_count":46,"area":"mllm"},{"id":"2309.09969","title":"Prompt a Robot to Walk with Large Language Models","created":"2023-09-18","cited_by_count":45,"area":null},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44,"area":null},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44,"area":"lr"},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2501.04693","title":"Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding","created":"2025-01-08","cited_by_count":42,"area":"vla"},{"id":"2402.02651","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","created":"2024-02-05","cited_by_count":41,"area":"mllm"},{"id":"2409.02084","title":"GraspSplats: Efficient Manipulation with 3D Feature Splatting","created":"2024-09-03","cited_by_count":41,"area":"mllm"},{"id":"2507.07136","title":"LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS","created":"2025-07-09","cited_by_count":41,"area":null},{"id":"2306.17840","title":"Statler: State-Maintaining Language Models for Embodied Reasoning","created":"2023-06-30","cited_by_count":40,"area":"wm"},{"id":"2403.19589","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2406.09798","title":"Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation","created":"2024-06-14","cited_by_count":39,"area":null},{"id":"2310.15127","title":"Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models","created":"2023-10-23","cited_by_count":37,"area":"agents"},{"id":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37,"area":null},{"id":"2412.14480","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","created":"2024-12-19","cited_by_count":37,"area":null},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2503.10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","created":"2025-03-13","cited_by_count":35,"area":"mllm"},{"id":"2401.12202","title":"OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics","created":"2024-01-22","cited_by_count":34,"area":null},{"id":"2407.10031","title":"LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments","created":"2024-07-14","cited_by_count":32,"area":"agents"},{"id":"2411.04999","title":"DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation","created":"2024-11-07","cited_by_count":32,"area":"mllm"},{"id":"2310.07968","title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","created":"2023-10-12","cited_by_count":31,"area":"lr"},{"id":"2403.07563","title":"Learning Generalizable Feature Fields for Mobile Manipulation","created":"2024-03-12","cited_by_count":31,"area":null},{"id":"2505.05800","title":"3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks","created":"2025-05-09","cited_by_count":31,"area":"vla"},{"id":"2303.07522","title":"Audio Visual Language Maps for Robot Navigation","created":"2023-03-13","cited_by_count":30,"area":null},{"id":"2505.05456","title":"SITE: towards Spatial Intelligence Thorough Evaluation","created":"2025-05-08","cited_by_count":29,"area":null},{"id":"2508.13446","title":"CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models","created":"2025-08-19","cited_by_count":29,"area":"vla"},{"id":"2410.12782","title":"In-Context Learning Enables Robot Action Prediction in LLMs","created":"2024-10-16","cited_by_count":27,"area":null},{"id":"2412.10402","title":"TANGO: Training-free Embodied AI Agents for Open-world Tasks","created":"2024-12-05","cited_by_count":27,"area":"agents"},{"id":"2312.14828","title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","created":"2023-12-22","cited_by_count":26,"area":null},{"id":"2402.14623","title":"RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation","created":"2024-02-22","cited_by_count":26,"area":null},{"id":"2402.05929","title":"An Interactive Agent Foundation Model","created":"2024-02-08","cited_by_count":25,"area":"agents"},{"id":"2403.08032","title":"LG-Traj: LLM Guided Pedestrian Trajectory Prediction","created":"2024-03-12","cited_by_count":25,"area":null},{"id":"2405.05792","title":"RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation","created":"2024-05-09","cited_by_count":25,"area":null},{"id":"2507.13019","title":"Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities","created":"2025-07-17","cited_by_count":25,"area":"lr"},{"id":"2305.12427","title":"VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations","created":"2023-05-21","cited_by_count":23,"area":null},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2402.04648","title":"OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding","created":"2024-02-07","cited_by_count":22,"area":null},{"id":"2403.09412","title":"OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments","created":"2024-03-14","cited_by_count":22,"area":null},{"id":"2410.20220","title":"Neural Fields in Robotics: A Survey","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2408.01366","title":"Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation","created":"2024-08-02","cited_by_count":20,"area":null},{"id":"2410.18570","title":"Zero-shot Object Navigation with Vision-Language Models Reasoning","created":"2024-10-24","cited_by_count":19,"area":"lr"},{"id":"2411.17636","title":"MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation","created":"2024-11-26","cited_by_count":19,"area":"agents"},{"id":"2309.08138","title":"Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation","created":"2023-09-15","cited_by_count":18,"area":null},{"id":"2408.00254","title":"LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting","created":"2024-08-01","cited_by_count":18,"area":null},{"id":"2408.16228","title":"Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2410.03035","title":"SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2412.08331","title":"SLGaussian: Fast Language Gaussian Splatting in Sparse Views","created":"2024-12-11","cited_by_count":18,"area":null},{"id":"2412.13654","title":"GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting","created":"2024-12-18","cited_by_count":18,"area":"distill"},{"id":"2401.04181","title":"Language-Conditioned Robotic Manipulation with Fast and Slow Thinking","created":"2024-01-08","cited_by_count":17,"area":"lr"},{"id":"2305.07716","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","created":"2023-05-12","cited_by_count":16,"area":"lr"},{"id":"2401.02814","title":"Object-Centric Instruction Augmentation for Robotic Manipulation","created":"2024-01-05","cited_by_count":16,"area":null},{"id":"2402.11498","title":"Verifiably Following Complex Robot Instructions with Foundation Models","created":"2024-02-18","cited_by_count":16,"area":null},{"id":"2404.14249","title":"CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding","created":"2024-04-22","cited_by_count":16,"area":null},{"id":"2503.18107","title":"PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding","created":"2025-03-23","cited_by_count":16,"area":null},{"id":"2505.01458","title":"A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI","created":"2025-05-01","cited_by_count":16,"area":null},{"id":"2309.15065","title":"Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2402.10340","title":"On the Vulnerability of LLM/VLM-Controlled Robotics","created":"2024-02-15","cited_by_count":15,"area":"mllm"}],"next_cursor":"100"}