An open API service indexing awesome lists of open source software.

https://github.com/skywardai/paper_gallery

Papers gallery for using LLMs ability over dataset
https://github.com/skywardai/paper_gallery

ai data data-science llm medicine neural-network research security

Last synced: 3 months ago
JSON representation

Papers gallery for using LLMs ability over dataset

Awesome Lists containing this project

README

          

# The papers gallery

This directory contains the papers that as reference for the project.

|No|Title|Studio Lab|Kaggle|Colab|Description|Researcher|
|---|---|---|---|---|---|---|
|1|[Text2SQL is Not Enough: Unifying AI and Databases with TAG](text2SQL/2408.14717v1.pdf)||||Answering natural language questions over databases|[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|2|[LOTUS: Enabling Semantic Queries with LLMs Over Tables of Unstructured and Structured Data](mimic_paper/LOTUS.pdf)||||Answering natural language questions over databases|[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|

# Medical

![](img/MIMIC_Mind%20Map.svg)

## mimic-iv paper

|No|Title|Studio Lab|Kaggle|Colab|Description|Researcher|
|---|---|---|---|---|---|---|
|1|[MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](mimic_paper/MIMIC-Extract.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|2|[Democratizing EHR analyses with FIDDLE: a flexible data- driven preprocessing pipeline for structured clinical data](mimic_paper/FIDDLE.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|3|[An Extensive Data Processing Pipeline for MIMIC-IV](mimic_paper/MIMICIV%20Pipeline.pdf)||||Basic structure of data extract pipeline|[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|4|[Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events](mimic_paper/Event%20Stream%20GPT.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|5|[INTERPOLATION-PREDICTION NETWORKS FOR IRREGULARLY SAMPLED TIME SERIES](mimic_paper/IP-Net.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|6|[MULTI-TIME ATTENTION NETWORKS FOR IRREGULARLY SAMPLED TIME SERIES](mimic_paper/mTAN.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|7|[Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series](mimic_paper/HeTVAE.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|8|[Multitask learning and benchmarking with clinical time series data](mimic_paper/MIMIC-III%20Benchmarking.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|9|[Using Clinical Notes with Time Series Data for ICU Management](mimic_paper/Fusion.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|
|10|[Predicting in-hospital mortality by combining clinical notes with time-series data](mimic_paper/BERT.pdf)|||||[Bowen](https://github.com/Aisuko), [Yuwei](https://github.com/wangyuweikiwi)|

## mimic-iv datasets

|No|Title|List on Kaggle|Huggingface|Description|Researcher|
|---|---|---|---|---|---|
|1|Raw MIMIC-IV v1.0|[![Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/code/aisuko/pre-download-mimic-iv-v1-0-dataset)||Private|[Yuwei](https://github.com/wangyuweikiwi)|
|2|Raw MIMIC-IV v2.0|[![Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/datasets/skywardai/mimic-iv-classification-regression-tasks/data)||Public|[Yuwei](https://github.com/wangyuweikiwi)|
|3|Raw MIMIC-IV v2.0||[![Huggingface](https://huggingface.co/datasets/huggingface/badges/resolve/main/dataset-on-hf-sm-dark.svg)](https://huggingface.co/datasets/aisuko/mimic_iv_classification_regression_tasks)|Public|[Yuwei](https://github.com/wangyuweikiwi)|

# Security

## Machine unlearning

|No|Title|Studio Lab|Kaggle|Colab|Description|Researcher|
|---|---|---|---|---|---|---|
|1|[Machine Unlearning](security/1912.03817v3.pdf)||||A mechanism that user can remove harmful data from llm in real time|Arjuna|
|2|[Does Refusal Training in LLMs Generalize to the Past Tense?](security/2407.11969v2.pdf)||||LLM attack|[Tyson](https://github.com/Murkeee)|

# References

* https://huggingface.co/datasets/huggingface/badges/blob/main/README.md?code=true
* https://github.com/Aisuko/generative-ai