Fan Luo's Projects
TensorFlow code and pre-trained models for BERT
Framework for assembling causal probabilistic models from text and software.
Code and website for DAL (Discriminative Active Learning) - a new active learning algorithm for neural networks in the batch setting. For the blog:
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.
MAFIA: Multiple Application Framework for GPU architectures
A state-of-the-art semi-supervised method for image recognition
'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.
comparing stand up comedians using natural language processing
Open Source Computer Vision Library
'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.
Official Repository for 'Practical Natural Language Processing' by O'Reilly
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
code and files for workshop
Read, Collaborate and talk about scientific papers
Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.
assignment
AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker