↓Skip to main content

🏢 University of British Columbia

ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning
·8117 words·39 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Question Answering 🏢 University of British Columbia
ARR: A novel zero-shot prompting method significantly boosts LLM performance on diverse question-answering tasks by explicitly incorporating question analysis, information retrieval, and step-by-step …
A Study on the Performance of U-Net Modifications in Retroperitoneal Tumor Segmentation
·1561 words·8 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Segmentation 🏢 University of British Columbia
ViLU-Net, a novel U-Net modification using Vision-xLSTM, achieves superior retroperitoneal tumor segmentation accuracy and efficiency, exceeding existing state-of-the-art methods.
Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images
·2021 words·10 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Generation 🏢 University of British Columbia
New attack fools breast ultrasound AI using subtle text prompts.
Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks
·4411 words·21 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 University of British Columbia
Swan & ArabicMTEB: New dialect-aware Arabic embedding models and benchmark achieve state-of-the-art performance, addressing limitations of existing multilingual models.