Maximilian Du

Try, Try Again: Behavior Cloning for Novel Test-Time Scenarios

Maximilian Du, Sasha Khazatsky, Tobias Gerstenberg, Chelsea Finn

Ongoing Project

When faced with a difficult task, a human may try different learned strategies until they discover a successful approach. As an example, a human may try pushing on a door first. If it does not move, then the human will try to pull. In this project, we try to create a similar try-retry paradigm for robots. The proposed try-retry paradigm would leverage a set of strategies learned from expert data and a time-to-success model that helps the agent decide when and how to switch strategies.

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

Maximilian Du, Suraj Nair, Dorsa Sadigh, Chelsea Finn

Robotics: Science and Systems 2023

Often, robot data isn't shared across projects. We present a new way that past project data can be used to improve downstream learning. We select relevant data from a large dataset of robot interactions, which augments a small set of task demonstrations for use in a behavior cloning algorithm. Relevance is determined through a state-action embedding that is trained directly with the past project data. We show, in simulation and on real robots, a meaningful improvement of our Behavior Retrieval method over baselines.

Website  /  Paper  /  Code

Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning

Maximilian Du*, Olivia Lee*, Suraj Nair, Chelsea Finn

Robotics: Science and Systems 2022

When accomplishing certain tasks, we benefit from using other modalities like audio. In this project, we show that robots can also benefit from audio data while accomplishing visually-occluded tasks. We learn policies end-to-end from RGB vision and audio from a gripper-mounted microphone. The learned policies can accomplish difficult tasks, like extracting keys from a bag when the keys are not initially visible.

Website  /  Paper  /  Code

Improving LSTM Neural Networks for Better Short-Term Wind Power Predictions

Maximilian Du

IEEE Renewable Energy and Power Engineering (REPE) 2019

Ultra-short term wind power predictions can play an important role in the stability of a renewable energy power grid. In this project, I used auxiliary weather forecast data to improve such predictions.

Paper  /  Code

Looking Under the Hood of DetectGPT

CS224N Final Project 2023

As Large Language Models (LLMs) become more advanced, there's a strong push to create effective detection algorithms. In this work, we look at a new detection algorithm originally proposed by Mitchell et al: DetectGPT. We proposed and tested ways of improving DetectGPT by focusing on parts of speech. We also demonstrated that DetectGPT can be partially fooled by an adversarial prompt. Finally, we tested DetectGPT on ChatGPT.

Paper

Sixteen Pixels is (Almost) All You Need: Crafting Parameterized Image Uncrumpling Models

Winning CS231N Final Project 2022

Phone document scans can suffer from distortions from a crinkled document. We created a decrumpling model that will take in an image of a crumpled document and smooth it out. We find that an adversarial paradigm with a small PatchGAN yields the most realistic results with the best quantitative scores as well.

Paper  /  Code

Thompson Sampling Simulator

CS 109 Winning Final Project 2021

Thompson sampling is one approach to exploration, where you sample from belief distributions and test the samples in the real world. It is one way of balancing exploration and exploitation. In this simulation of Thompson sampling, we visualize ants finding a good location for a nest. We also implement Tandem Running, which allows ants to "persuade" other ants, resulting in faster convergence.

Code

Media Annotator

This simple Python-based program allows you to use keyboard shortcuts to annotate audio, video, and live events with timestamped comments. The program will export your annotations to copy-and-paste text that you can add to any literature review notes. I rely heavily on this tool to review hours of videos for my book.

Recently, I've also made a book annotator that allows you to make page-specific notes. This allows you digitize your annotations for physical books.

Code

Coding Basics

As a researcher, I often find that I use the same code many times in different applications. To help, I've been working on a large repository of code basics. It's a collection of code snippets that help with model debugging, plot making, basic PyTorch models, and more.

Code

Automatic Source Vetter

This webscraping software will search RSS, YouTube, and Twitter accounts of your choice for new content with relevant keywords. It saves these to a SQL database for later perusal. I've also included a slurry of specialty website parsers for my whale book research. While you probably won't need these, the specialty parsers demonstrate the modularity of this software.

Code (still actively updating)

Can I Train my Robot like my Dog?

Reinforcement learning in AI has origins in animal training in the 1900's. While much has been abstracted away since then, I take another look at this original connection between CS and psychology. In this 90-minute talk, I explore the interplay between challenges faced in robot labs and dolphin stadiums. We explore behavior cloning, reinforcement techniques, models of learning, and more.

I give this talk twice a year at Stanford Splash, an educational outreach program that serves students in the Bay area, especially students from underrepresented and disadvantaged backgrounds.

Slide Deck Sample  /  Stanford Splash Program

Section Leading for CS 106A/B

I was a section leader for Stanford's introductory CS106A and intermediate CS106B computer science courses. As a section leader, I hosted weekly sessions to review lecture content in a small group setting. I also hosted office hours, graded homeworks, provided interactive feedback, and helped graded exams.

Section Leading Program

Mentor for Deep Learning Portal

I will be a mentor for the Deep Learning Portal outreach program starting Fall 2023. The Portal is a program created from the IRIS lab and the Stanford CS department, designed to help disadvantaged students learn AI by providing access to existing online courses and hosting live office hours. I will be helping with office hours, where I will be debugging code and answering conceptual questions.

Deep Learning Portal Program