AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization
cs.CV
Submitted: 2026-09-17
Updated: 2026-09-17
Code: https://github.com/xandery-geek/Awesome-AI-Smart-Glasses-Papers
Terminology
Sources
- A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
- VisionClaw: Always-On AI Agents through Smart Glasses
- EgoNav: Egocentric Scene-aware Human Trajectory Prediction
- EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations
- Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data
- EgoSelf: From Memory to Personalized Egocentric Assistant
- Grounding 3D Scene Affordance From Egocentric Interactions
- Aria Everyday Activities Dataset
- EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
- CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark
- WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
- QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question Answering
- AI for Service: Proactive Assistance with AI Glasses
- MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning
- Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
- CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation
- Can Large Language Models Understand Preferences in Personalized Recommendation?
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
- MemGPT: Towards LLMs as Operating Systems
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models