-->
Computer Science PhD ∈ Northwestern University
I am a third-year Ph.D. candidate in the Computer Science department at Northwestern University, advised by Professor Yan Chen and Han Liu in MAGICS lab.
My primary research interest lies in the intersection between Machine Learning, Health Care, and Financial Data.
Topics I am currently working on (Machine/Deep Learning):
Topics I had worked on in the past (Before my PhD study):
Besides the school and research work, I have found my interests in lots of things over time including photography, hiking and traveling.
I serve as Research Assistant in Dashun's Lab.
Our workshop paper, ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction, has been accepted by the 2nd ACM SIGSPATIAL International Workshop on the Human Mobility Prediction Challenge, where we achieved the top 1 DTW score.
Our paper OutEffHop: A Principled Outlier-Efficient Attention Layer from Dense Associative Memory Models is accepted by ICML'2024.
Our workshop paper Outlier-Efficient Hopfield Layers for Large Transformer-Based Models and Fast Adaptation and Robust Quantization of Multi-Modal Foundation Models from Associative Memory: A Case Study in SpeechLM are accepted by ICML ES-FoMo'2024.
I serve as TA of CS150.
I serve as TA of CS348.
I serve as TA of CS327.
I hold a PC role in the industry track of EMNLP 2023.
I work as an EMNLP 2023 reviewer.
A conference paper "Open-Ended Multi-Modal Relational Reason for Video Question Answering " is accepted by RO-MAN 2023.
I work as ACL 2023 && ACL ARR April 2023 Reviewer
A conference paper "IGN : Implicit Generative Networks" is accepted by ICMLA 2022.
I start my PhD study in Northwestern University!
Computer Science PhD @ Northwestern University
Sept. 2022GPA 3.92/4.0, MSIT @ Northwestern University (Transfer to CS PhD program)
Sept. 2021GPA 3.7/4.0, VQA-related research @ Machine Learning Lab
Augest. 2020 - May 2021Graduate with High Hornor, GPA 3.53/4.0, NLP-related research @ Machine Learning Lab, Dean List
Jan. 2018 - May 2020Transfer to Georgia Institute of Technology with GPA 3.65/4.0
Sept. 2016 - Dec 2017Integrated Modern Hopfield Networks into the Knowledge-augmented Language Model to address limitation in self-attention architecture and Foundation Model, e.g. no-op outlier in the training;Explored the interpretability of Jailbreak strategies in safety-aligned LLMs by employing in-context learning and outlier analysis to enhance the alignment and safety of superhuman AI system; Applied LLMs to address multivariate time-series challenges, including in-context time series forecasting, Limit Order Book dynamics prediction, and Cross-sectional Regression Time-series Analysis; Developed efficient Hyperparameter Optimization (HPO) methods to optimize models for time series predictions with Tree-structured Parzen Estimator (TPE) and Genetic Algorithm.
Dec. 2021 - PresentWork in Distributed Deep Reinforcement Leaning by implementing IQN model with Wasserstein GAN algorithm; Designed policy evaluation experiment with Atari Game Database using the fixed policy inputting and compare the result with the baseline of the fixed policy; Developed policy optimization on the IQN model with the Wasserstein GAN algorithm
Sept. 2021 - Nov. 2021Worked on model-free reinforcement learning to show SOTA performance with our physical simulator; Implemented PPO, SAC algorithm to get and plot the reward of the reinforcement learning in our physical simulator; Published a paper in progress- “ RobLAX- A Differentiable Robotics Framework for Physics Augmented Reinforcement Learning”
May. 2021 - Sept. 2021Worked on the brat problem and built the pipeline of the NLP labeling application; Researched on the polysemy problem and used the BERT model to label the target words and phrase; Researched on the Operational Transformation Algorithm to make sure the several contributors modifying together in cloud.
Sept. 2020 - May 2021Worked on Continuous Neuro-Symbolic VQA. In particular researched on the problem of soft logic function; Designed and implemented the reasoning model based on Bert, Bi-direction LSTM and Stack-NMN. Evaluated the performance with other VQA models; Researched on the Video Question Answering and designed the model with R(2+1)D to detect the action and movement of objects in videos; Publishing a paper in progress - Differentiable End-to-End Program Executor for Sample and Computationally Ef;icient VQA.
Aug. 2020 - Oct 2020Researched the visual question answering problem. Visual question answering using NS-VQA algorithm to classify the relationship of different objects in images and give out the answer of the GQA problem. Researched on the reasoning work and used the bi-directional LSTM to make some improvement on the reasoning work in VQA;Understood what the function of the VQA works and what the latest technology on solving the VQA problem
Aug. 2019 - May 2020Developed a pipeline capable of analyzing the adsorption energy in chemical reactions by using Python and ASE API; Implemented a machine learning model capable to analyzing the structure of chemical molecular.
Jan. 2019 - May 2020Developed a pipeline that collects data provided by the stadium networks and analyzes collected data to give out a precise result to stadium staffs; Delivered a website tool capable to setting up a remote database for the LoPT database team.
Jan. 2018 - Dec 20182nd ACM SIGSPATIAL International Workshop on the Human Mobility Prediction Challenge
Oct. 2024Review by ICLR'2024
May. 2024Review by ICLR'2024
May. 2024Review by ICML'2025
May. 2024Accepted by Efficient Systems for Foundation Models II@ ICML2024
June. 2024Accepted by Efficient Systems for Foundation Models II@ ICML2024
June. 2024Accepted by ICML'2024
Jan. 2024Review by ICLR'2024
Jan. 2024Review by ICLR'2024
Aug. 2023Review by Information Systems
Aug. 2023Review by ICML' 2025
Jan. 2023ICMLA'2022 - 2022 21st IEEE International Conference on Machine Learning and Applications
March. 2022Sept. 2021
Under Reviewed by ACL-SDProc 2024
Jan. 2021RO-MAN'2023 - 2023 32nd IEEE International Conference on Robot and Human Interactive Communication
Dec. 2020Oct 2020
FICC'2021 - Proceedings of the 2021 Future of Information and Communication Conference
Oct 2019I grade students’ projects and exams and provide feedback to facilitate improvement; Have a solid understanding of algorithms in KMM, Gradient Model and Neural-Networks; Provide students with the means to succeed by holding ofkice hours and responding to questions online
Augest. 2020 - May 2021I automated the process of sending security alerts through Slack and Email by developing an app that would be deployed on all windows machines at Splunk; Developed a pipeline that detects sensitive kiles used by customer support and implements the required retention policies.
June. 2020 - Augest 2020I designed and developed a customer support tool that automatically suggests answers to customer questions, by using Python/React.js/ Flask/Electron/TensorFlow and NLTK; Created a pipeline that updates the customer support knowledge base with customer support feedback from the previous tool, it potentially saved 35% of the original time.
May 2019 - Augest 2019I delivered a pipeline capable of predicting Twitter usernames from local residents' real names; Implemented a visualization tool that describes the analysis with several kinds of statistic chart
Augest 2018 - September 2018I contributed work to the construction of a website tool which provides customers cloud-computing server; Designed a pipeline that tests machine learning functions which are inside web servers and compares results with common machine learning algorithms using Python and TensorFlow.
June 2018 - Augest 2018I developed a pipeline capable of scrawling data from the Common Vulnerability and Exposures website using Python and Selenium; Delivered the scrawled data into PostgreSQL
May 2017 - July 2017Movable infusion stand (201120560457X)
Robin Luo
December 2013 in Hangzhou
High Hornor of Graduateions
May 2020 in Atlanta
Hopefully before I am 30-year-ago, I can
Visit 30 countries / regions (7/30)
🇨🇳China, 🇭🇰Hong Kong, 🇯🇵Japan, 🇺🇸United States, 🇨🇦Canada, 🇻🇳Vietnam, 🇸🇬Singapore.
Visit 30 provinces in China (13/30)
Beijing, Zhejiang, Fujian, Hainan, Guangdong, Jiangshu Heilongjiang, Tianjin, Hong Kong, Shandong, Anhui, Shanxi, Shanghai.
Visit 30 states in the US (29/30)
❄️AK, 🌉CA, 🏂 CO, 📃 CT, 🐼DC, 🍊 FL, 🍑 GA, 🌋HI, 💨IL, 🏁IN, 🚜IA, 🏇KY, 🔮MA, 🐢MD, 🚘MI, ♈ MO, 🌟MN, ✈ NC, 🐍 NH, 💡NJ, 🏜️NV, 🗽NY, 🌹 OR, 🌊 RI, 🌴 SC, 🎸 TN, 🗼TX, 🍺WI, ☔WA.
Visit 30 National Parks in the US (47/30)
Herbert Hoover NHS, Indiana Dunes NL, Golden Gate NRA, Boston African American NHS, Boston NHP, Statue of Liberty NM, Federal Hall NMEM, Fort Point NHS, Fort Pulaski NM, Ice Age NST, Korean War Veterans Memorial, Lincoln Memorial, Pullman Memorial, Pearl Harbor Memorial ,Salem Maritime NHS, Sleeping Bear Dunes NL, Yosemite NP, Vietnam Veterans Memorial, White House, Gateway Arch NP, Rocky Mountain NP, Florissant Fossil Beds NM, Lincoln Home NHS, Ulysses S. Grant NHS, Lewis & Clark NHT, San Francisco Maritime NHP, Alcatraz Island, Point Reyes NS, Presidio of San Francisco, Muir Woods NM, Juan Bautista de Anza NHT, Great Smoky Mountains NP, Big South Fork NRNA, Obed Wild and Scenic River, Mammoth Cave NP, Blue Ridge Parkway, Manhattan Project NHP, Congaree NP, Minute Man NHP, Saugus Iron Works NHS, Mount Rainier NP, North Cascades NP, Olympic NP, Ross Lake NRA, Lake Chelan NRA, Wing Luke Museum Affiliated Area, Lewis & Clark NHP
Visit 30 Airpots (40/30)
ZSYT, KORD, KJFK, ZSHC, ZSPD, KATL, KDTW, ZYHB, ZBTJ, ZBAA, ZJSY, ZLXY, KLAX, KSFO, KLEX, KEWR, KLGA, VHHH, KMIA, KSJC, KMCO, KMSP, KLAN, KDFW, KDEN, ZSAM, KIAH, KAUS, KBWI, KDCA, KSEA, KCID, KSLC, KLAS, KHNL, KIAD, KBRL, ZGGG, ZGSZ, VVTS
Take flights with 30 Airplane Companies (18/30)
HU, CA, DL, AA, UA, CZ, MU, JD, CX, MF, KA, F9, NK, WN, AS, AC, 9K, NK
Finish 300,000 kilometers flight by air (238,593/300,000)
© 2024 Robin(Haozheng) Luo