About
Research & Development
New AI Model Enhances Brain Age Prediction Using 3D MRI Scans
TLDR: A new AI model, the Deeply Supervised Multitask Autoencoder (DSMT-AE), accurately predicts biological brain age from 3D T1-weighted MRI scans. It uses multitask...
Research & Development
OpenMed NER: Advancing Biomedical Text Analysis with Efficient Open-Source AI
TLDR: OpenMed NER introduces open-source, domain-adapted transformer models for biomedical named-entity recognition (NER). By combining lightweight domain-adaptive pre-training (DAPT) with parameter-efficient LoRA, it achieves...
Research & Development
Semantic Encryption: A New Approach for Private and Useful Cloud LLM Interactions
TLDR: Semantic Encryption (SE) is a novel framework that allows users to interact securely and effectively with Cloud-based Large Language Models (CLLMs). It works...
Research & Development
A New Approach to Securing Language Models from Hidden Backdoors
TLDR: DUP is a new framework that combines advanced detection of poisoned inputs with efficient unlearning techniques to remove hidden backdoor vulnerabilities in language...
Research & Development
Unraveling the Authorship of Multilingual AI-Generated Texts
TLDR: This research paper introduces and investigates the problem of multilingual authorship attribution, aiming to identify whether a text was written by a human...
Research & Development
Visual Prompts: A Double-Edged Sword for AI Vision Models
TLDR: A new method called Prompt-in-Image embeds text instructions directly into images for Vision-Language Models (VLMs). It significantly improves Qwen2.5-VL's accuracy and reduces hallucination...