Fan Luo's Projects
This article gives an overview of large language models, including the underlying architecture, training process, and applications of these models.
TensorFlow code and pre-trained models for BERT
A doctoral dissertation titled "Towards the Advancement of Open-Domain Textual Question Answering Methods". The dissertation presents several innovative solutions aimed at addressing the challenges faced by ODQA systems and improving the performance.
GPGPU-Sim provides a detailed simulation model of a contemporary GPU (such as NVIDIA's Fermi and GT200 architectures) running CUDA and/or OpenCL workloads and now includes an integrated (and validated) energy model, GPUWattch.
Project
'Semi-Supervised Teacher-Student Architecture for Relation Extraction' adapt Mean Teacher, a denoising semi-supervised framework, to improve the performance of relation extraction by incorporating both labeled and unlabeled data in the training process.
'Scientific Discovery as Link Prediction in Influence and Citation Graphs' introduces a novel framework for scientific discovery by treating the problem as a link prediction task in influence and citation graphs.
mafia_experiments
assignment
classify the tweet as 'neutral or no emotion' or as one, or more, of eleven given emotions that best represent the mental state of the tweeter: