About
Research & Development
Contrast-CAT: A Clearer Lens for Explaining Text Classifier Behavior
TLDR: Contrast-CAT is a novel method that enhances the interpretability of Transformer-based text classifiers. It refines token-level attributions by contrasting input activations with reference...
Research & Development
A Unified LLM Approach for Complex Interactive Applications
TLDR: A new research paper introduces ContextLoRA and ContextGear, a novel framework that enables a single large language model (LLM) to efficiently handle diverse...
Research & Development
Navigating Imperfect Data: Advancing AI Learning in Real-World Scenarios
TLDR: This thesis presents a comprehensive suite of algorithms designed to enable deep neural networks to learn effectively from limited and imperfect real-world data....
Research & Development
Deep Learning for African Wildlife: A Comparative Study of Image Classification Models
TLDR: A new study evaluates deep learning models for classifying African wildlife images (buffalo, elephant, rhinoceros, zebra). While the Vision Transformer (ViT-H/14) achieved the...
Research & Development
Automating Software Architecture with Collaborative AI Agents
TLDR: MAAD (Multi-Agent Architecture Design) is a new framework that uses a team of four specialized AI agents (Analyst, Modeler, Designer, Evaluator) to automate...
Research & Development
VN-MTEB: A New Benchmark for Vietnamese Text Embeddings
TLDR: VN-MTEB is a new, large-scale benchmark for evaluating text embedding models in Vietnamese. It comprises 41 datasets across six NLP tasks, created by...