About
Research & Development
Rethinking Project Assessments for the Generative AI Era
TLDR: This paper proposes a new conceptual model for Project-Based Assessment (PBA) in higher education, adapting to the rise of Generative AI (GenAI). It...
Research & Development
Streamlining LLM Collaboration with SafeSieve’s Adaptive Pruning
TLDR: SafeSieve is a new algorithm for multi-agent LLM systems that addresses redundant communication and high token overhead. It uses a progressive, adaptive pruning...
Research & Development
Boosting Euphemism Detection in Multilingual AI Through Sequential Language Training
TLDR: A research paper explores how sequential fine-tuning improves euphemism detection across five languages (English, Spanish, Chinese, Turkish, Yorùbá) using XLM-R and mBERT models....
Research & Development
Advancing Uncrewed Aerial Vehicles with Transformer and Large Language Models
TLDR: This research paper reviews how Transformer and Large Language Models (LLMs) are transforming Uncrewed Aerial Vehicles (UAVs) by improving their perception, decision-making, and...
Research & Development
Advancing Bioacoustic Understanding Through Comprehensive Machine Learning Study
TLDR: A large-scale empirical study identifies that combining self-supervised pre-training with supervised post-training on diverse bioacoustic and general audio data yields state-of-the-art, generalizable bioacoustic...
Research & Development
AdaRing: A New Approach to Efficiently Adapt Vision-Language Models
TLDR: AdaRing is a novel fine-tuning framework that significantly improves the efficiency of adapting large Vision-Language Models (VLMs) for various tasks. It achieves this...