-->
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 the MAGICS Lab.
My primary research interest lies in the intersection of Machine Learning, Health Care, and Financial Data.
Topics I am currently working on (Machine/Deep Learning):
Topics I worked on in the past (before my Ph.D. studies):
Besides schoolwork and research, I have developed interests in many activities over time, including photography, hiking, and traveling.
2025.1: Our paper Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models has been accepted by ICLR 2025.
2025.1: I am serving as a TA for CS368.
2025.1: I received $1,000 in research funding from the OpenAI Research Access Program.
2024.9: I am serving as a Research Assistant in Dashun's Lab.
2024.10: 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.
2024.7: Our workshop papers 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 have been accepted by ICML ES-FoMo 2024.
2024.5: Our paper OutEffHop: A Principled Outlier-Efficient Attention Layer from Dense Associative Memory Models has been accepted by ICML 2024.
2024.4: I received $5,000 in research funding from the OpenAI Research Access Program.
2023.6: I served as a Program Committee (PC) member for the industry track of EMNLP 2023.
2023.4: Our conference paper Open-Ended Multi-Modal Relational Reasoning for Video Question Answering was accepted by RO-MAN 2023.
2022.10: Our conference paper IGN: Implicit Generative Networks was accepted by ICMLA 2022.
2022.9: I started my Ph.D. studies at 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 a knowledge-augmented language model to address limitations in self-attention architectures and foundation models, such as no-op outliers during training. Explored the interpretability of jailbreak strategies in safety-aligned LLMs by employing in-context learning and outlier analysis to enhance alignment and safety in superhuman AI systems. Applied LLMs to 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 for time-series prediction using the Tree-structured Parzen Estimator (TPE) and Genetic Algorithm.
Dec. 2021 - PresentWorked on distributed deep reinforcement learning by implementing the IQN model with the Wasserstein GAN algorithm. Designed a policy evaluation experiment using the Atari Game Database with fixed policy input and compared results with a baseline fixed policy. Developed policy optimization for the IQN model using the Wasserstein GAN algorithm.
Sept. 2021 - Nov. 2021Worked on model-free reinforcement learning to achieve state-of-the-art performance in a physical simulator. Implemented PPO and SAC algorithms to compute and visualize reinforcement learning rewards. Contributed to a paper in progress, RobLAX-A Differentiable Robotics Framework for Physics-Augmented Reinforcement Learning.
May. 2021 - Sept. 2021Developed an NLP labeling pipeline for the brat annotation tool. Researched polysemy problems and applied the BERT model for target word and phrase labeling. Studied the Operational Transformation Algorithm to enable collaborative real-time editing in the cloud.
Sept. 2020 - May 2021Worked on Continuous Neuro-Symbolic Visual Question Answering (VQA), particularly researching soft logic functions. Designed and implemented a reasoning model combining BERT, bidirectional LSTM, and Stack-NMN, and evaluated its performance against other VQA models. Researched Video Question Answering and developed a model using R(2+1)D to detect object actions and movements. Contributed to a paper in progress, “Differentiable End-to-End Program Executor for Sample and Computationally Efficient VQA.”
Aug. 2020 - Oct 2020Researched the Visual Question Answering (VQA) problem using the NS-VQA algorithm to classify object relationships in images and answer GQA questions. Investigated reasoning mechanisms and improved performance using bidirectional LSTMs. Explored the functionality and latest advancements in VQA technology.
Aug. 2019 - May 2020Developed a computational pipeline for analyzing adsorption energy in chemical reactions using Python and the ASE API. Implemented a machine learning model to analyze chemical molecular structures.
Jan. 2019 - May 2020Developed a data pipeline that collects and analyzes stadium network data to provide precise insights for stadium staff. Built a website tool for 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 USENIX Security'2025
May. 2024Review by USENIX Security'2025
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. 2024Accepted by ICLR'2025
Jan. 2024Review by ICML'2025
Aug. 2023Review by Information Systems
Aug. 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 turn 30 years old, 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, Jiangsu, Heilongjiang, Tianjin, Hong Kong, Shandong, Anhui, Shanxi, Shanghai.
Visit 30 states in the US (30/30)
❄️ AK, 🌉 CA, 🏂 CO, 📃 CT, 🐼 DC, 🍊 FL, 🍑 GA, 🌋 HI, 💨 IL, 🏁 IN, 🚜 IA, 🏇 KY, 🔮 MA, 🐢 MD, 🚘 MI, ♈ MO, 🌟 MN, ✈ NC, 🐍 NH, 💡 NJ, 🏜️ NV, 🗽 NY, 🏈 OH, 🌹 OR, 🌊 RI, 🌴 SC, 🎸 TN, 🗼 TX, 🍺 WI, ☔ WA.
Visit 30 National Parks in the US (51/30)
Indiana Dunes NP, Yosemite NP, Mount Rainier NP, North Cascades NP, Olympic NP, Great Smoky Mountains NP, Gateway Arch NP, Rocky Mountain NP, Mammoth Cave NP, Congaree NP, Boston NHP, Manhattan Project NHP, Minute Man NHP, Lewis & Clark NHP, San Francisco Maritime NHP, Golden Gate NRA, Ross Lake NRA, Lake Chelan NRA, Big South Fork NRRA, Herbert Hoover NHS, Lincoln Home NHS, Ulysses S. Grant NHS, Boston African American NHS, Fort Point NHS, Saugus Iron Works NHS, Salem Maritime NHS, Statue of Liberty NM, Fort Pulaski NM, Muir Woods NM, Fort McHenry NM, Florissant Fossil Beds NM, Lewis & Clark NHT, Star-Spangled Banner NHT, Juan Bautista de Anza NHT, Sleeping Bear Dunes NL, Ice Age NST, Point Reyes NS, Obed WSR, Korean War Veterans Memorial, Lincoln Memorial, Pullman Memorial, Pearl Harbor Memorial, Vietnam Veterans Memorial, White House, Alcatraz Island, Presidio of San Francisco, Washington Monument, World War II Memorial, Wing Luke Museum Affiliated Area, Blue Ridge Parkway, Baltimore-Washington Parkway.
Visit 30 Airports (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.
Fly with 30 Airlines (18/30)
HU, CA, DL, AA, UA, CZ, MU, JD, CX, MF, KA, F9, NK, WN, AS, AC, 9K, NK.
Accumulate 300,000 kilometers of air travel (238,593/300,000)
© 2025 Robin(Haozheng) Luo