When In Manila

Canva Now Understands Chronically Online Language—Here’s How It Works

Once, using technology meant learning how machines talk: code, commands, and keyboard shortcuts. Somewhere between social media, algorithms, and group chats, ...
IEEE

NICE: Non-Functional Requirements Identification, Classification, and Explanation Using Small Language Models

Abstract: Accurate identification and classification of Non-Functional Requirements (NFRs) is essential for informed architectural decision-making and maintaining software quality. Numerous language ...
IEEE

Constructing a Medical Domain Functional Knowledge Graph with Large Language Models

Abstract: The integration of medicine and artificial intelligence is creating novel opportunities to gather, analyze, and generate groundbreaking medical insights from the vast expanse of medical ...
GitHub

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In ...
GitHub

LucaVirus: Modeling the Evolutionary and Functional Landscape of Viruses with a Unified Genome-Protein Language Model

OpenVirus Datasets are now available on HuggingFace. The corpus comprises 15.7 million non-redundant viral sequences (including 10.4 million nucleotide sequences and 5.2 million protein sequences).