Posts by Collection

Github Cheatsheet

1. userid and password store: git config --global credential.helper store

C++ Tutorial

1. C++ tutorial

C++ Guidelines

1. A set of guidelines written by the C++ authors
2. A shorter set from guidelines distilled from the first link
3. Some good points about style and safety
4. Code snippets easy to draw inspiration

Get Advisor

Mosh for low-bandwidth ssh

1. Client side install if you are using Chrome
2. Server side insatll if you are using Ubuntu: sudo apt-get install mosh
3. Don’t forget adding ssh key info
4. Kill past sessions except the existing one: kill $(ps --no-headers --sort=start_time -C mosh-server -o pid | head -n -1)

Login to Jupyter Notebook remotely

1. On server: jupyter notebook --no-browser --port=8889
2. On local terminal: ssh -N -f -L localhost:8888:localhost:8889 username@serverIP
3. On local browser: Open http://localhost:8888/ with token

Sparse Convolutions for Faster Object Recognition

Wei Hao and Shivaram Venkataraman, "Sparse Convolutions for Faster Object Recognition", AI Systems Workshop at Symposium on Operating Systems Principles(SOSP), 2019. http://learningsys.org/sosp19/assets/papers/21_CameraReadySubmission_sparse_conv_aisys19_final.pdf

Learning Amyloid Pathology Progression from Longitudinal PiB-PET Images in Preclinical Alzheimer’s Disease

Wei Hao, Nicholas M. Vogt, Zihang Meng, Seong Jae Hwang, Rebecca L. Koscik, Sterling C. Johnson, Barbara B. Bendlin, and Vikas Singh, "Learning Amyloid Pathology Progression from Longitudinal PiB-PET Images in Preclinical Alzheimer’s Disease", International Symposium on Biomedical Imaging (ISBI), 2020. https://ieeexplore.ieee.org/abstract/document/9098571

Serving DNNs like Clockwork: Performance Predictability from the Bottom Up

Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, Jonathan Mace, "Serving DNNs like Clockwork: Performance Predictability from the Bottom Up", 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2020. https://arxiv.org/abs/2006.02464

A Tale of Two Models: Constructing Evasive Attacks on Edge Models

Wei Hao, Aahil Awatramani, Jiayang Hu, Chengzhi Mao, Pin-Chun Chen, Eyal Cidon, Asaf Cidon, Junfeng Yang, "A Tale of Two Models: Constructing Evasive Attacks on Edge Models", Fifth Conference on Machine Learning and Systems (MLSys), 2022. https://arxiv.org/abs/2204.10933

MGit: A Model Versioning and Management System

Wei Hao*, Daniel Mendoza*, Rafael Mendes, Deepak Narayanan, Amar Phanishayee, Asaf Cidon, Junfeng Yang, "MGit: A Model Versioning and Management System", The Forty-first International Conference on Machine Learning (ICML), 2024. https://www.microsoft.com/en-us/research/uploads/prodnew/2024/06/mgit_icml_2024.pdf

Learning to Rewrite: Generalized LLM-Generated Text Detection

Wei Hao, Ran Li, Weiliang Zhao, Junfeng Yang, and Chengzhi Mao. "Learning to Rewrite: Generalized LLM-Generated Text Detection", arXiv preprint arXiv:2408.04237 (2024). https://arxiv.org/abs/2408.04237

Nazar: Monitoring and Adapting ML Models on Mobile Devices

Wei Hao, Zixi Wang, Lauren Hong, Lingxiao Li, Nader Karayanni, AnMei Dasbach-Prisk, Chengzhi Mao, Junfeng Yang, Asaf Cidon, "Nazar: Monitoring and Adapting ML Models on Mobile Devices", The 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025.

I Can Hear You: Selective Robust Training for Deepfake Audio Detection

Zhang, Zirui, Wei Hao, Aroon Sankoh, William Lin, Emanuel Mendiola-Ortiz, Junfeng Yang, and Chengzhi Mao. "I Can Hear You: Selective Robust Training for Deepfake Audio Detection", arXiv preprint arXiv:2411.00121 (2024). https://arxiv.org/abs/2411.00121

Characterizing the Prevalence of LLM-Generated Malicious Emails

Diversity Helps Jailbreak Large Language Models

Weiliang Zhao, Daniel Ben-Levi, Wei Hao,Junfeng Yang, Chengzhi Mao. "Diversity Helps Jailbreak Large Language Models", arXiv preprint arXiv:2411.04223 (2024). https://arxiv.org/abs/2411.04223

Oral Presentation at ISBI 2020

Published: April 03, 2020

This presentation talks about a novel trainable network diffusion model that infers the propagation dynamics of amyloid pathology, which conditioned on individual-level structural connectivity network.

Oral Presentation at OSDI 2020

Published: November 03, 2020

This presentation talks about a fully distributed DNN model serving system that achieves predictable end-to-end performance.

CSEE4121 - Computer Systems for Data Science, Spring 22

Undergraduate course, Columbia University, Computer Science Department, 2022

TA