WEZZEL NEWS

Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching

Researchers have proposed a new framework for self-supervised learning called Distribution Matching ...

SAS: Segment Anything Small for Ultrasound -- A Non-Generative Data Augmentation Technique for Robust Deep Learning in Ultrasound Imaging

Researchers have developed a data augmentation technique called Segment Anything Small (SAS) to impr...

Deep Contrastive Unlearning for Language Models

Researchers have proposed a new framework called Deep Contrastive Unlearning for fine-Tuning (DeepCU...

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling

Researchers have proposed a new approach to improve the performance of large language models (LLMs) ...

AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Method Case Study

Researchers have developed AI University (AI-U), a framework that uses large lan...

ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model

Researchers have developed a large language model called ClinicalGPT-R1 for dise...

COLORA: Efficient Fine-Tuning for Convolutional Models with a Study Case on Optical Coherence Tomography Image Classification

Researchers have introduced COLORA (Convolutional Low-Rank Adaptation), a method...

Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric

Researchers have developed a new algorithm called the Unified Path Planner (UPP)...