{"list":"other","total":81,"rows":[{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2401.16158","title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","created":"2024-01-29","cited_by_count":293},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33},{"id":"2510.14359","title":"AI for Service: Proactive Assistance with AI Glasses","created":"2025-10-16","cited_by_count":20},{"id":"2604.23570","title":"EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks","created":"2026-04-26","cited_by_count":20},{"id":"2511.16661","title":"Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations","created":"2025-11-20","cited_by_count":19},{"id":"2606.09828","title":"Latent Spatial Memory for Video World Models","created":"2026-06-08","cited_by_count":17},{"id":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16},{"id":"2511.00153","title":"EgoMI: Learning Active Vision and Whole-Body Manipulation from Egocentric Human Demonstrations","created":"2025-10-31","cited_by_count":15},{"id":"2603.22264","title":"UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos","created":"2026-03-23","cited_by_count":14},{"id":"2605.09874","title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","created":"2026-05-11","cited_by_count":13},{"id":"2603.20169","title":"EgoForge: Goal-Directed Egocentric World Simulator","created":"2026-03-20","cited_by_count":12},{"id":"2510.23981","title":"TeleEgo: Benchmarking Egocentric AI Assistants in the Wild","created":"2025-10-28","cited_by_count":11},{"id":"2605.06747","title":"HumanNet: Scaling Human-centric Video Learning to One Million Hours","created":"2026-05-07","cited_by_count":11},{"id":"2608.02580","title":"Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data","created":"2026-08-03","cited_by_count":11},{"id":"2512.06721","title":"ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild","created":"2025-12-07","cited_by_count":10},{"id":"2606.17200","title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","created":"2026-06-15","cited_by_count":10},{"id":"2510.14861","title":"LabOS: The AI-XR Co-Scientist That Sees and Works With Humans","created":"2025-10-16","cited_by_count":9},{"id":"2604.08534","title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","created":"2026-04-09","cited_by_count":8},{"id":"2606.12604","title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","created":"2026-06-10","cited_by_count":8},{"id":"2607.14183","title":"Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning","created":"2026-07-15","cited_by_count":8},{"id":"2604.01966","title":"Ego-Grounding for Personalized Question-Answering in Egocentric Videos","created":"2026-04-02","cited_by_count":7},{"id":"2605.27074","title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","created":"2026-05-26","cited_by_count":7},{"id":"2606.04970","title":"Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance","created":"2026-06-03","cited_by_count":7},{"id":"2606.09669","title":"SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks","created":"2026-06-08","cited_by_count":7},{"id":"2606.19930","title":"MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization","created":"2026-06-18","cited_by_count":7},{"id":"2607.20033","title":"HOST:Robots Acquire Manipulation Skills in Seconds from a Single Human Video","created":"2026-07-22","cited_by_count":7},{"id":"2601.10323","title":"ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding","created":"2026-01-15","cited_by_count":6},{"id":"2603.28732","title":"Pandora: Articulated 3D Scene Graphs from Egocentric Vision","created":"2026-03-30","cited_by_count":6},{"id":"2604.03486","title":"VisionClaw: Always-On AI Agents through Smart Glasses","created":"2026-04-03","cited_by_count":6},{"id":"2606.06194","title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","created":"2026-06-04","cited_by_count":6},{"id":"2606.09461","title":"H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions","created":"2026-06-08","cited_by_count":6},{"id":"2606.24422","title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","created":"2026-06-23","cited_by_count":6},{"id":"2602.23893","title":"AoE: Always-on Egocentric Human Video Collection for Embodied AI","created":"2026-02-27","cited_by_count":5},{"id":"2603.22529","title":"Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos","created":"2026-03-23","cited_by_count":5},{"id":"2605.31557","title":"EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision","created":"2026-05-29","cited_by_count":5},{"id":"2606.17054","title":"Human Universal Grasping","created":"2026-06-15","cited_by_count":5},{"id":"2605.24456","title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","created":"2026-05-23","cited_by_count":4},{"id":"2606.09243","title":"EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video","created":"2026-06-08","cited_by_count":4},{"id":"2607.11487","title":"LightMem-Ego: Your AI Memory for Everyday Life","created":"2026-07-13","cited_by_count":4},{"id":"2605.04227","title":"Pro$^2$Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks","created":"2026-05-05","cited_by_count":3},{"id":"2605.07299","title":"EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams","created":"2026-05-08","cited_by_count":3},{"id":"2605.10936","title":"Personal Visual Context Learning in Large Multimodal Models","created":"2026-05-11","cited_by_count":3},{"id":"2605.18734","title":"EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos","created":"2026-05-18","cited_by_count":3},{"id":"2606.19926","title":"MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management","created":"2026-06-18","cited_by_count":3},{"id":"2606.26093","title":"ForceBand: Learning Forceful Manipulation with sEMG","created":"2026-06-24","cited_by_count":3},{"id":"2608.13113","title":"EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory","created":"2026-08-13","cited_by_count":3},{"id":"2602.16682","title":"SAW-Bench: Learning Situated Awareness in the Real World","created":"2026-02-18","cited_by_count":2},{"id":"2603.13741","title":"Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision","created":"2026-03-14","cited_by_count":2},{"id":"2604.23691","title":"Intention-Aware Semantic Agent Communications for AI Glasses","created":"2026-04-26","cited_by_count":2},{"id":"2601.19502","title":"VisGuardian: A Lightweight Group-based Privacy Control Technique For Front Camera Data From AR Glasses in Home Environments","created":"2026-01-27","cited_by_count":1},{"id":"2602.13479","title":"GLIMPSE : Real-Time Text Recognition and Contextual Understanding for VQA in Wearables","created":"2026-02-13","cited_by_count":1},{"id":"2602.22340","title":"Conversational Successes and Breakdowns in Everyday Smart Glasses Use","created":"2026-02-25","cited_by_count":1},{"id":"2602.22455","title":"Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge","created":"2026-02-25","cited_by_count":1},{"id":"2604.05519","title":"Active noise cancellation on open-ear smart glasses","created":"2026-04-07","cited_by_count":1},{"id":"2604.23141","title":"UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks","created":"2026-04-25","cited_by_count":1},{"id":"2604.23148","title":"PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks","created":"2026-04-25","cited_by_count":1},{"id":"2605.10404","title":"Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitable","created":"2026-05-11","cited_by_count":1},{"id":"2605.11782","title":"Urban Risk-Aware Navigation via VQA-Based Event Maps for People with Low Vision","created":"2026-05-12","cited_by_count":1},{"id":"2605.16797","title":"EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices","created":"2026-05-16","cited_by_count":1},{"id":"2606.07431","title":"OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Vision","created":"2026-06-05","cited_by_count":1},{"id":"2606.09142","title":"Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models","created":"2026-06-08","cited_by_count":1},{"id":"2606.09547","title":"Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?","created":"2026-06-08","cited_by_count":1},{"id":"2606.15859","title":"EPIC: A System Framework for Efficient Egocentric Perception on Embodied AR Glasses","created":"2026-06-14","cited_by_count":1},{"id":"2607.15868","title":"EgoExoMoCap: Distributed Ego-Exo Human Motion Capture","created":"2026-07-17","cited_by_count":1},{"id":"2608.08285","title":"Ego-OSCAR: Egocentric Open source Stereo CAptuRe System","created":"2026-08-08","cited_by_count":1}],"next_cursor":null}