About
Research & Development
SePA: An AI Agent for Proactive and Personalized Health Coaching
TLDR: SePA (Search-enhanced Predictive AI Agent) is a novel LLM health coaching system that integrates personalized machine learning and retrieval-augmented generation. It uses wearable...
Research & Development
AI’s Grasp of Gags: Fine-Tuned Decoders Match Encoders in Humor Classification
TLDR: A study investigated Large Language Models' (LLMs) ability to classify humor, finding that a fine-tuned decoder model (GPT-4o) performed as well as the...
Research & Development
Unlocking Creative Potential: A New Training Method Boosts LLM Diversity Without Sacrificing Quality
TLDR: A new research paper introduces DQO (Diversity-Quality Optimization), a novel training method for Large Language Models (LLMs) that uses Determinantal Point Processes (DPPs)...
Research & Development
Deep Learning on Mobile Images: A Step Towards Accessible Skin Disease Diagnosis
TLDR: This research introduces a novel approach to skin disease classification using deep learning models on a large dataset of over 27,000 mobile-acquired images...
Research & Development
PLaMo 2: Hybrid Architecture and Synthetic Data Drive Japanese LLM Performance
TLDR: PLaMo 2 is a new series of Japanese-focused large language models by Preferred Networks. It features a hybrid Samba-based architecture that evolves to...
Research & Development
Advancing Global Land Surface Temperature Measurement with a Hybrid Modeling Approach
TLDR: Researchers have developed the Mechanism Model-Machine Learning (MM-ML) framework, a novel approach that combines physical models with machine learning to achieve highly accurate...