{"list":"other","total":62,"rows":[{"id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","created":"2026-03-30","cited_by_count":309},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47},{"id":"2609.10522","title":"Show-Harness: Just a VLM Agent Can Play Robots","created":"2026-09-09","cited_by_count":20},{"id":"2510.07134","title":"TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking","created":"2025-10-08","cited_by_count":17},{"id":"2312.01059","title":"Swarm-GPT: Combining Large Language Models with Safe Motion Planning for Robot Choreography Design","created":"2023-12-02","cited_by_count":15},{"id":"2501.14377","title":"Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight","created":"2025-01-24","cited_by_count":15},{"id":"2602.09657","title":"AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild","created":"2026-02-10","cited_by_count":15},{"id":"2506.19283","title":"AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration","created":"2025-06-24","cited_by_count":11},{"id":"2603.14363","title":"AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control","created":"2026-03-15","cited_by_count":11},{"id":"2512.23219","title":"MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios?","created":"2025-12-29","cited_by_count":10},{"id":"2504.10334","title":"Flying Hand: End-Effector-Centric Framework for Versatile Aerial Manipulation Teleoperation and Policy Learning","created":"2025-04-14","cited_by_count":9},{"id":"2603.25038","title":"$\\pi$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation","created":"2026-03-26","cited_by_count":7},{"id":"2502.02054","title":"RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation","created":"2025-02-04","cited_by_count":6},{"id":"2601.21602","title":"AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation","created":"2026-01-29","cited_by_count":6},{"id":"2607.12477","title":"Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence","created":"2026-07-14","cited_by_count":6},{"id":"2602.00551","title":"APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation","created":"2026-01-31","cited_by_count":5},{"id":"2603.14336","title":"UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding","created":"2026-03-15","cited_by_count":5},{"id":"2603.22846","title":"CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models","created":"2026-03-24","cited_by_count":5},{"id":"2603.28032","title":"CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence","created":"2026-03-30","cited_by_count":5},{"id":"2505.20710","title":"Hierarchical Instruction-aware Embodied Visual Tracking","created":"2025-05-27","cited_by_count":4},{"id":"2512.21085","title":"Global End-Effector Pose Control of an Underactuated Aerial Manipulator via Reinforcement Learning","created":"2025-12-24","cited_by_count":4},{"id":"2602.01266","title":"Reinforcement Learning for Active Perception in Autonomous Navigation","created":"2026-02-01","cited_by_count":4},{"id":"2603.19822","title":"HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks","created":"2026-03-20","cited_by_count":4},{"id":"2604.02241","title":"UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models","created":"2026-04-02","cited_by_count":4},{"id":"2604.16298","title":"FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation","created":"2026-04-17","cited_by_count":4},{"id":"2605.01371","title":"ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue","created":"2026-05-02","cited_by_count":4},{"id":"2505.20783","title":"FM-Planner: Foundation Model Guided Path Planning for Autonomous Drone Navigation","created":"2025-05-27","cited_by_count":3},{"id":"2603.23079","title":"AirSimAG: A High-Fidelity Simulation Platform for Air-Ground Collaborative Robotics","created":"2026-03-24","cited_by_count":3},{"id":"2604.02020","title":"Are VLMs Lost Between Sky and Space? LinkS$^2$Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence","created":"2026-04-02","cited_by_count":3},{"id":"2604.17190","title":"LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation","created":"2026-04-19","cited_by_count":3},{"id":"2604.21453","title":"Instance-level Visual Active Tracking with Occlusion-Aware Planning","created":"2026-04-23","cited_by_count":3},{"id":"2604.26567","title":"AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision","created":"2026-04-29","cited_by_count":3},{"id":"2607.20061","title":"ReferTrack: Referring Then Tracking for Embodied Visual Tracking","created":"2026-07-22","cited_by_count":3},{"id":"2509.14126","title":"CrazyMARL: Decentralized Direct Motor Control Policies for Cooperative Aerial Transport of Cable-Suspended Payloads","created":"2025-09-17","cited_by_count":2},{"id":"2512.10773","title":"AERMANI-Diffusion: Regime-Conditioned Diffusion for Dynamics Learning in Aerial Manipulators","created":"2025-12-11","cited_by_count":2},{"id":"2603.06573","title":"Fly360: Omnidirectional Obstacle Avoidance within Drone View","created":"2026-03-06","cited_by_count":2},{"id":"2603.25275","title":"V2U4Real: A Real-world Large-scale Dataset for Vehicle-to-UAV Cooperative Perception","created":"2026-03-26","cited_by_count":2},{"id":"2605.17776","title":"CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization","created":"2026-05-18","cited_by_count":2},{"id":"2607.10180","title":"ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception","created":"2026-07-11","cited_by_count":2},{"id":"2607.16193","title":"Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMs","created":"2026-07-17","cited_by_count":2},{"id":"2608.01802","title":"CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning","created":"2026-08-03","cited_by_count":2},{"id":"2608.12707","title":"SAP-Nav: Spatial Semantic Representation Meets Active Perception for Hierarchical Open-Vocabulary Object Navigation","created":"2026-08-13","cited_by_count":2},{"id":"2409.10283","title":"ASMA: An Adaptive Safety Margin Algorithm for Vision-Language Drone Navigation via Scene-Aware Control Barrier Functions","created":"2024-09-16","cited_by_count":1},{"id":"2410.08507","title":"Decentralized Uncertainty-Aware Active Search with a Team of Aerial Robots","created":"2024-10-11","cited_by_count":1},{"id":"2603.07699","title":"C$^2$-Explorer: Contiguity-Driven Task Allocation with Connectivity-Aware Task Representation for Decentralized Multi-UAV Exploration","created":"2026-03-08","cited_by_count":1},{"id":"2603.12908","title":"GoalSwarm: Multi-UAV Semantic Coordination for Open-Vocabulary Object Navigation","created":"2026-03-13","cited_by_count":1},{"id":"2603.13919","title":"OpenCOOD-Air: Prompting Heterogeneous Ground-Air Collaborative Perception with Spatial Conversion and Offset Prediction","created":"2026-03-14","cited_by_count":1},{"id":"2605.04574","title":"VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking","created":"2026-05-06","cited_by_count":1},{"id":"2606.08533","title":"Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning","created":"2026-06-07","cited_by_count":1},{"id":"2606.14772","title":"ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering","created":"2026-06-09","cited_by_count":1},{"id":"2606.16621","title":"Reinforcement Learning with Inner-loop Dynamics Estimator for Aerial Manipulation under Uncertainty","created":"2026-06-15","cited_by_count":1},{"id":"2606.22756","title":"HERCULES: An Open-Source Simulation Framework for Heterogeneous Multi-Robot SLAM, Collaborative Perception, and Exploration","created":"2026-06-22","cited_by_count":1},{"id":"2606.25880","title":"USS: Unifying Spatial-Semantic Prompting for End to End Embodied Visual Tracking","created":"2026-06-24","cited_by_count":1},{"id":"2606.27603","title":"Learning to Throw: Agile and Accurate Cable-Suspended Payload Delivery with a Quadrotor","created":"2026-06-25","cited_by_count":1},{"id":"2606.31073","title":"MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning","created":"2026-06-30","cited_by_count":1},{"id":"2607.02764","title":"MorphQuad: Morphable Quadrotor for Superhuman Maneuverability, Manipulation, and Resiliency","created":"2026-07-02","cited_by_count":1},{"id":"2607.09078","title":"Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method","created":"2026-07-10","cited_by_count":1},{"id":"2607.11529","title":"Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory","created":"2026-07-13","cited_by_count":1},{"id":"2607.15004","title":"CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking","created":"2026-07-16","cited_by_count":1},{"id":"2607.29009","title":"D-VLC: Decentralized Vision-Language Collaboration for Heterogeneous Embodied Multi-Robot Systems in Unknown Environments","created":"2026-07-31","cited_by_count":1},{"id":"2609.03483","title":"Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps","created":"2026-09-03","cited_by_count":1},{"id":"2609.08402","title":"Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method","created":"2026-09-08","cited_by_count":1}],"next_cursor":null}