arXiv AI July 3, 2026 By Cristian-Gabriel Florea, Stelian Sp\^inu

VisionAId: An Offline-First Multimodal Android Assistant for People with Visual Impairment, Featuring Personalized Object Retrieval

arXiv:2607. 02371v1 Announce Type: cross Abstract: Over 285 million people worldwide live with a visual impairment, for whom everyday tasks such as avoiding obstacles, locating personal belongings, recognizing familiar faces, or handling cash remain persistent obstacles to personal autonomy.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 7

OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance

arXiv:2607. 03213v1 Announce Type: cross Abstract: We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind and low-vision users.

By Mengzhang Li, Yuan Yao

multimodal safety

arXiv AI

Aug 3

Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning

arXiv:2607. 29353v1 Announce Type: cross Abstract: With the ever-increasing pervasiveness of smart edge devices, the demand is growing for applications that can be tailored to users (e.

By Douwe den Blanken, Martin Lefebvre, Charlotte Frenkel

llms benchmarks safety

arXiv AI

Jul 7

STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition

arXiv:2607. 03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, cloud inference adds latency and privacy risk, and fine-tuned LLM pipelines turn general-purpose models into task-specific classifiers.

By Nirhoshan Sivaroopan, Albert Zomaya, Kanchana Thilakarathna

llms rag nlp fine-tuning benchmarks safety

arXiv AI

1d ago

EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input

arXiv:2608. 15614v1 Announce Type: cross Abstract: The use of multimodal LLMs (MLLMs) for egocentric video understanding with wearable devices is constrained by the token budget.

By Matteo Stoiber, Niels Buus Lassen

llms multimodal

arXiv Machine Learning

Jul 30

RAG-HAR+: Towards Cost-Efficient LLM-Based Human Activity Recognition for Edge Deployment

arXiv:2607. 26631v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments.

By Hansi Karunarathna, Nirhoshan Sivaroopan, Chamara Madarasingha, Anura Jayasumana, Kanchana Thilakarathna

llms rag agents efficiency benchmarks

arXiv AI

Jun 3

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

arXiv:2606. 03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware.

By Glenn Jocher, Jing Qiu, Mengyu Liu, Shuai Lyu, Fatih Cagatay Akyon, Muhammet Esat Kalfaoglu

llms computer-vision

Related stories

OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance

Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning

STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition

EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input

RAG-HAR+: Towards Cost-Efficient LLM-Based Human Activity Recognition for Edge Deployment

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models