{"total":31,"rows":[{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2502.11007","title":"Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations","created":"2025-02-16","cited_by_count":14,"area":null},{"id":"2404.13274","title":"Augmented Object Intelligence with XR-Objects","created":"2024-04-20","cited_by_count":12,"area":null},{"id":"2506.00717","title":"Vid2Coach: Transforming How-To Videos into Task Assistants","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2409.08250","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2604.09698","title":"Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation","created":"2026-04-06","cited_by_count":5,"area":null},{"id":"2410.22177","title":"Analyzing Multimodal Interaction Strategies for LLM-Assisted Manipulation of 3D Scenes","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2602.08914","title":"Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2602.00793","title":"SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2603.12701","title":"Seeing Eye to Eye: Enabling Cognitive Alignment Through Shared First-Person Perspective in Human-AI Collaboration","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2412.12681","title":"Everyday AR through AI-in-the-Loop","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2603.26646","title":"Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2505.01578","title":"Grounding Task Assistance with Multimodal Cues from a Single Demonstration","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2507.17248","title":"Reality Proxy: Fluid Interactions with Real-World Objects in MR via Abstract Representations","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2508.04011","title":"StepWrite: Adaptive Planning for Speech-Driven Text Generation","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2512.17172","title":"PILAR: Personalizing Augmented Reality Interactions with LLM-based Human-Centric and Trustworthy Explanations for Daily Use Cases","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2601.17622","title":"Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2602.03059","title":"From Speech-to-Spatial: Grounding Utterances on A Live Shared View with Augmented Reality","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.05132","title":"ARGaze: Autoregressive Transformers for Online Egocentric Gaze Estimation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.08445","title":"Alfa: Attentive Low-Rank Filter Adaptation for Structure-Aware Cross-Domain Personalized Gaze Estimation","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.12533","title":"Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2608.11017","title":"R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2405.18620","title":"RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2508.15752","title":"\"Does the cafe entrance look accessible? Where is the door?\" Towards Geospatial AI Agents for Visual Inquiries","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2604.04905","title":"ClickAIXR: On-Device Multimodal Vision-Language Interaction with Real-World Objects in Extended Reality","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.08062","title":"From Gaze to Guidance: Interpreting and Adapting to Users' Cognitive Needs with Multimodal Gaze-Aware AI Assistants","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2606.00182","title":"The New Social Image: How AI Competency and AI Proactivity Influence Self- and Peer-Perceptions in the Workplace","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.01437","title":"How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.19793","title":"AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.04706","title":"VoCa: Designing Speech-Canvas Interaction for Voice-Based Conversational Agents","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.17128","title":"EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}