Medical Accessibility and Assistive Technologies
Research on LLMs for developing assistive technologies for patients with disabilities or impairments, including communication aids and accessibility solutions
Medical Accessibility and Assistive Technologies
Research on Large Language Models in Medical Accessibility and Assistive Technologies
Breaking Barriers in Sign Language Technology
A Retrieval-Enhanced Approach to Multilingual Sign Language Generation
AI-Powered Throat Wearable Restores Natural Speech
Breakthrough technology combining wearable sensors with LLMs for stroke patients
Merging Minds and Machines
How LLMs are Revolutionizing Brain-Computer Interfaces for Communication
AI-Powered Navigation for the Visually Impaired
Using Vision-Language Models to Guide Independent Walking
Bridging the Human-Robot Gap for Elderly Care
Multimodal Fusion of Voice and Gestures via LLMs
Measuring the Storytelling Power of Images
A framework for quantifying semantic complexity in visual content
Enhancing AI Vision with Ego-Augmented Learning
Using Egocentric Perspectives to Improve Understanding of Daily Activities
Enhancing AAC with Advanced Language Models
Making character-based communication faster and more accurate for users with disabilities
Breaking Down Medical Jargon
Using LLMs to improve health literacy through plain language adaptation
Decoding Thoughts Into Text
Breakthrough in Neural Spelling BCI Systems
Enhancing Vision in AI: The SPARC Approach
Solving the visual attention decay problem in multimodal large language models
SensorChat: Revolutionizing Sensor Data Interaction
The first end-to-end QA system for long-term multimodal sensor monitoring
Making Medical Information Patient-Friendly
AI-Powered Q&A Generation from Discharge Letters
Enhancing AI Understanding of Daily Activities
Skeleton-based approach improves vision-language models for healthcare applications
Echo-Teddy: Advancing Support for Autism Education
LLM-powered social robot creating meaningful interactions for autistic students
Advancing Emotional Intelligence in AI
Benchmarking and enhancing emotional capabilities in multimodal LLMs
Multimodal Empathy: Beyond Text-Only Support
Creating emotionally intelligent avatars with text, speech, and visual cues
Optimizing Vision-Language Models for Edge Devices
Advancing VLMs for resource-constrained environments in healthcare and beyond
AI-Powered Speech Analysis for Dementia Detection
Using robotic conversational systems to identify cognitive impairment markers
Revolutionizing BCI with Language Models
Enhancing brain-computer interfaces through LLM integration
Gesture-Enhanced Speech Recognition
Bridging communication gaps for patients with language disorders
Smart Environments Enhanced by Context-Aware AI
Merging Location Data, Activity Recognition and LLMs for Personalized Interactions
Optimizing AI Navigation Aids for the Visually Impaired
Understanding BLV User Preferences in LVLM Responses
Empowering the Visually Impaired with AI Vision
How Large Multimodal Models Transform Daily Life for People with Visual Impairments
ChatMotion: Revolutionizing Human Motion Analysis
A Multi-Agent Approach for Responsive Motion Intelligence
MLLMs for Parent-Child Communication
Leveraging AI to understand joint attention in early language development
AI-Powered Speech Recall Assessment
Automating multilingual speech comprehension evaluation with LLMs
Teaching AI to Hear Stress in Speech
Fine-tuning Whisper ASR for inclusive prosodic analysis
MLLMs for the Visually Impaired
How Multimodal LLMs are Transforming Visual Interpretation Tools
Next-Gen Wi-Fi Sensing
Overcoming Generalizability Challenges in Wireless Sensing Technologies
EgoBlind: Enhancing AI Vision for the Visually Impaired
The first egocentric VideoQA dataset from blind individuals' perspectives
AI-Enhanced Neural Implants for PTSD
A dual-loop system integrating brain implants with AI wearables
GuideDog: AI Vision for the Visually Impaired
A groundbreaking multimodal dataset to enhance mobility for the blind and low-vision community
Gaze-Driven AI Assistants
LLM-Enhanced Robots That Read Your Intentions
Advanced Skeletal Action Recognition
Enhancing Security and Surveillance Through Relational Graph Networks
Revolutionizing Human-Robot Interaction with Gaze and Speech
Foundation Models Enable More Natural, Accessible Robot Control
AI Advocates for Disabled Students
Using Social Robots to Support Mediation in Higher Education
Explaining Smart Home AI with LLMs
Making activity recognition transparent and trustworthy
Speak Ease: Giving Voice to Everyone
Using LLMs to Enhance Expressive Communication for Speech-Impaired Individuals
Smart Video Counting with AI
Using LLMs to Count Repetitive Actions Across Diverse Scenarios
Enhancing AI's Social Intelligence
Using Iterative Loop Structures to Improve Video Understanding
Breaking Barriers with Cued Speech AI
MLLM-Driven Hand Modeling for Accessible Communication
Making AI See for the Blind
Evaluating Multimodal LLMs as Visual Assistants for Visually Impaired Users
AI-Powered Scene Understanding for Assistive Robots
Enhancing mobility solutions with advanced semantic segmentation
AI-Powered Language Analysis for Children's Speech
NLP Solutions for More Efficient Developmental Language Assessments
AI-Powered Reading Support for Dyslexia
Using LLMs to enhance reading comprehension in real-time
Breaking Boundaries in IMU-Based Activity Recognition
Leveraging LLMs for Fine-Grained Movement Detection
Seamless Information Gathering in Conversations
How AI can naturally acquire user data through engaging chats
SceneScout: Unlocking Street Views for Blind Users
AI Agent Technology for Pre-Travel Visual Exploration
RadarLLM: Privacy-First Motion Understanding
Leveraging Large Language Models for Radar-Based Human Motion Analysis
