About
Research & Development
Crafting Authentic AI Personas: A New Approach to Synthetic Data Generation
TLDR: The PILOT framework introduces a two-phase method for steering large language models to generate synthetic data with precise psycholinguistic profiles. By translating natural...
Research & Development
Bridging Biology and AI: Lateral Connections Enhance Convolutional Neural Networks
TLDR: This research introduces two novel Convolutional Neural Network (CNN) models that integrate lateral connections, a key feature of the mammalian visual cortex. The...
Research & Development
Decoding Slang: How AI’s Informal Language Differs from Human Expression
TLDR: A study compared human and AI-generated slang, finding that while large language models (LLMs) are creative, their slang usage shows systematic biases. LLMs...
Research & Development
Diff-Feat: A New Approach to Multi-Label Classification Using Diffusion Model Features
TLDR: Diff-Feat is a new framework for multi-label classification that extracts and fuses intermediate features from pre-trained diffusion-Transformer models for both images and text....
Research & Development
Optimizing In-Context Learning: A Kernelized and Information-Theoretic Approach to Example Selection
TLDR: KITE is a novel, information theory-driven framework for selecting optimal examples for In-Context Learning (ICL) in large language models. It addresses limitations of...
Research & Development
Addressing Unwanted Brand Presence in AI-Generated Images
TLDR: CIDER is a new framework that tackles 'brand bias' in text-to-image AI models, where generic prompts often lead to images featuring dominant commercial...