Li Ding | 丁立

I'm a 4th-year Ph.D. candidate at UMass Amherst CICS, advised by Lee Spector. I work closely with Scott Niekum (UMass), Joel Lehman (StabilityAI), Jeff Clune (UBC, DeepMind), and also spent time at Google Research and Meta.

Before Ph.D., I was a full-time research engineer at MIT with Lex Fridman and Bryan Reimer, and concurrently a graduate student at MIT CSAIL. I did my master's at Univ. of Rochester with Chenliang Xu.


Scholar / Github / Twitter / LinkedIn / CV

11/2023 - I'm on the lookout for job opportunities in both the industry and academia, starting 09/2024. If you feel that my background is a good fit for your organization, let's chat!


My research focus is efficient learning algorithms for large AI models, focusing on:

  • Alignment: preference-based learning, RLHF, and aligning models with human interests.
  • Open-Endedness: generative models and adaptive agents for diversity-driven tasks and/or in open-ended environments.
  • Interdiscipline - applications in quantum computing and human-computer interaction.

Before Ph.D., I worked on deep learning for autonomous driving, human behavior modeling, and action recognition.


Representative papers are highlighted.

Quality Diversity through Human Feedback
Li Ding, Jenny Zhang , Jeff Clune , Lee Spector , Joel Lehman
NeurIPS 2023: Agent Learning in Open-Endedness (ALOE) Workshop (Spotlight)
[project page] [arXiv] [code] [tutorial]

Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation
Li Ding, Masrour Zoghi, Guy Tennenholtz, Maryam Karimzadehgan
NeurIPS 2023: Workshop on Adaptive Experimental Design and Active Learning in the Real World (RealML)
[arXiv] [code]

Probabilistic Lexicase Selection
Li Ding, Edward Pantridge, Lee Spector
GECCO 2023
[paper] [arXiv] [code]

CLERA: A Unified Model for Joint Cognitive Load and Eye Region Analysis in the Wild
Li Ding, Jack Terwilliger, Aishni Parab, Meng Wang, Lex Fridman, Bruce Mehler, Bryan Reimer
ACM Transactions on Computer-Human Interaction, 2023
[paper] [arXiv]

Multi-Objective Evolutionary Architecture Search for Parameterized Quantum Circuits
Li Ding, Lee Spector
Entropy (Special Issue: Quantum Machine Learning), 2023

Objectives Are All You Need: Solving Deceptive Problems Without Explicit Diversity Maintenance
Ryan Boldi, Li Ding, Lee Spector
NeurIPS 2023: Agent Learning in Open-Endedness Workshop

Lee Spector, Li Ding, Ryan Boldi
Genetic Programming Theory and Practice XX, 2023

Optimizing Neural Networks with Gradient Lexicase Selection
Li Ding, Lee Spector
ICLR 2022
[paper] [video] [poster] [code]

Going Faster and Hence Further with Lexicase Selection
Li Ding, Ryan Boldi, Thomas Helmuth, Lee Spector
GECCO 2022 (poster)

Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
Li Ding, Lee Spector
GECCO 2022: Quantum Optimization Workshop
[paper] [arXiv]

Lexicase Selection at Scale
Li Ding, Ryan Boldi, Thomas Helmuth, Lee Spector
GECCO 2022: Large-Scale Evolutionary Optimization and Learning Workshop
[paper] [arXiv]

Value of Temporal Dynamics Information in Driving Scene Segmentation
Li Ding, Jack Terwilliger, Rini Sherony, Bryan Reimer, Lex Fridman
IEEE Transactions on Intelligent Vehicles, 2021
[paper] [arXiv] [MIT DriveSeg Dataset]
Press coverage: [MIT News] [Forbes] [InfoQ] [TechCrunch]

Evolving Neural Selection with Adaptive Regularization
Li Ding, Lee Spector
GECCO 2021: NeuroEvolution at Work Workshop
[paper] [arXiv] [video]

Perceptual Evaluation of Driving Scene Segmentation
Li Ding, Rini Sherony, Bruce Mehler, Bryan Reimer
IEEE IV 2021
[paper] [video]

MIT-AVT Clustered Driving Scene Dataset: Evaluating Perception Systems in Real-World Naturalistic Driving Scenarios
Li Ding, Michael Glazer, Meng Wang, Bruce Mehler, Bryan Reimer, Lex Fridman
IEEE IV 2020
[paper] [video]

Arguing Machines: Human Supervision of Black Box AI Systems that Make Life-Critical Decisions
Lex Fridman, Li Ding, Benedikt Jenik, Bryan Reimer
CVPR 2019: Workshop on Autonomous Driving
[paper] [arXiv] [video]

MIT Advanced Vehicle Technology Study: Large-Scale Naturalistic Driving Study of Driver Behavior and Interaction with Automation
Lex Fridman, Daniel E. Brown, Michael Glazer, William Angell, Spencer Dodd, Benedikt Jenik, Jack Terwilliger, Julia Kindelsberger, Li Ding, Sean Seaman, Alea Mehler, Andrew Sipperley, Anthony Pettinato, Bobbie Seppelt, Linda Angell, Bruce Mehler, Bryan Reimer
IEEE Access, 2019
[paper] [arXiv] [video]

Human Interaction with Deep Reinforcement Learning Agents in Virtual Reality
Lex Fridman, Henri Schmidt, Jack Terwilliger, Li Ding
NeurIPS 2018: Deep RL Workshop

Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment
Li Ding, Chenliang Xu
CVPR 2018
[paper] [arXiv] [poster] [code]


TA for UMass COMPSCI 230: Computer Systems Principles (Summer 2021).
TA for MIT 6.S094: Deep Learning for Self-Driving Cars (Winter 2018-19).
TA for MIT 6.S099: Artificial General Intelligence (Winter 2019).

Conference Reviewer:
ICLR 2024, AAAI 2024, NeurIPS 2023, ICCV 2023, CVPR 2023, IJCNN 2022, IV 2021-2023, BMVC 2020, 2021, 2023, AutoUI 2020.

Journal Reviewer:
IEEE Transactions on Intelligent Vehicles, Quantum Machine Intelligence, Pattern Recognition, IEEE Transactions on Circuits and Systems for Video Technology.

AI Podcast:
Helped prepare interview questions, search for guest speakers, etc. for a podcast hosted by Lex Fridman about technology, science, and the human condition.
(Ranked #1 on Apple Podcasts in the technology category, 1M views on YouTube.)
(My personal favorite episode is Tomaso Poggio, highly recommended!)

Robocar Workshop:
Instructor for a summer/winter workshop at MIT with Dr. Tom Bertalan to college and high school students on building and programming autonomous robocars.

Last updated: 03/2024
Powered by Skeleton
Design inspired by Jon Barron