franciscoliu

AdversaryLossLandscape

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]

Awesome-GenAI-Unlearning

Awesome-Graph-LLM

A collection of AWESOME things about Graph-Related LLMs.

BERT-SDA

covid-19-prediction.github.io

Customer_churning

Customer attrition or “churning” (i.e., more and more customers are leaving their credit card services, such as canceling the cards) is an important problem faced by credit card companies. In this project, you are given a dataset of 10,000 customers with 18 attributes/features, such as, age, salary, marital status, credit card limit, credit card category, and so on. The goal is to build a model that can accurately predict churning customers and help understand the reason behind the scene. The 5-fold cross-validation results will be used in evaluating the performance.

GFAME

Code for Paper fair graph representation learning via diverse mixture-of-experts, WWW 2023

graphprompter

Implementation of GraphPrompter (The Web Conference 2024 Short Paper)

MLLMU-Bench

SKU

Official code implementation of SKU, Accepted by ACL 2024 Findings

franciscoliu/Awesome-GenAI-Unlearning

franciscoliu/graphprompter

Implementation of GraphPrompter (The Web Conference 2024 Short Paper)

franciscoliu/SKU

Official code implementation of SKU, Accepted by ACL 2024 Findings

franciscoliu/MLLMU-Bench

franciscoliu/GFAME

Code for Paper fair graph representation learning via diverse mixture-of-experts, WWW 2023

franciscoliu/Customer_churning

Customer attrition or “churning” (i.e., more and more customers are leaving their credit card services, such as canceling the cards) is an important problem faced by credit card companies. In this project, you are given a dataset of 10,000 customers with 18 attributes/features, such as, age, salary, marital status, credit card limit, credit card category, and so on. The goal is to build a model that can accurately predict churning customers and help understand the reason behind the scene. The 5-fold cross-validation results will be used in evaluating the performance.

franciscoliu/Awesome-Graph-LLM

A collection of AWESOME things about Graph-Related LLMs.

franciscoliu/BERT-SDA

franciscoliu/covid-19-prediction.github.io

franciscoliu/CS-103-PA01

franciscoliu/CS-103-pa03

franciscoliu/cs-103-PA2

franciscoliu/cs103a-cpa01

franciscoliu/CV-auto-generator

franciscoliu/detailed-virus-host.github.io

franciscoliu/FairAdj

Code for ICLR'2021 paper: On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections

franciscoliu/franciscoliu.github.io

Zheyuan's Personal Website

franciscoliu/LLM-UM-Reading

A list of large language models for user modeling (LLM-UM) papers.

franciscoliu/LLM-Unlearning-Paper-List

franciscoliu/loss-landscape

Code for visualizing the loss landscape of neural nets

franciscoliu/mixture-of-experts

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

franciscoliu/MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

franciscoliu/oct_arr_mllmu_bench

franciscoliu/semantic_indoor_seg

Sementation generation given the png image

franciscoliu/serverless-pdf

franciscoliu/simple-virus-host

franciscoliu/starter-hugo-academic

franciscoliu/tofu

Landing Page for TOFU

franciscoliu/vicky22birthday.github.io

franciscoliu/zheyuanliu-personal-web