Li Ding | 丁立

liding256@gmail.com ~~liding@{umass.edu, mit.edu}~~

I'm currently at Google DeepMind ( Mountain View), working on frontier safety & security research with a focus on AGI control.

Previously, I worked on pretraining, architecture, and runtime optimization for the Gemini Nano and Gemma models.

I received my PhD from UMass Amherst CICS, advised by Lee Spector. I also worked closely with Scott Niekum (UMass), Joel Lehman (formerly OpenAI), and Jeff Clune (UBC, DeepMind). My research focused on alignment for safety and creativity with diversity-driven approaches.

I interned at Google Research and Meta. Before PhD, I was a full-time researcher at MIT with Lex Fridman and Bryan Reimer, and a graduate student at MIT CSAIL. I did my master's at Univ. of Rochester with Chenliang Xu.

Research

My research focuses on aligning AI systems and enabling safe, self-directed agent learning in open-ended environments. I develop methods using reinforcement learning from human feedback (RLHF) to enhance the safety, creativity, and generalization of AI agents and large language models (LLMs).

My work spans multiple domains, including reinforcement learning, generative models, robotics, and computer vision. I'm also interested (and have published) in disciplines such as quantum ML, symbolic regression, program synthesis, and human-computer interaction. Before PhD, I worked on deep learning for autonomous driving, cognitive modeling, and video recognition.

Selected Publications

For a complete and up-to-date list of publications, please see Google Scholar.

Pareto-Optimal Learning from Preferences with Hidden Context
Ryan Boldi, Li Ding, Lee Spector, Scott Niekum
RLC 2025
[arXiv]

POPL learns Pareto-optimal policies or reward functions in RLHF, addressing hidden contexts such as diverse group preferences without needing group labels, offering safe and fair alignment of agents and LLMs.

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization
Li Ding, Jenny Zhang , Jeff Clune , Lee Spector , Joel Lehman
ICML 2024
NeurIPS 2023: ALOE Workshop (Spotlight)
[project page] [arXiv] [demo] [talk] [code] [tutorial]

QDHF learns diversity metrics from human feedback and uses those to optimize for the discovery of novel solutions, enhancing the task-solving capabilities of RL agents and the creativity of generative models.

Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation
Li Ding, Masrour Zoghi, Guy Tennenholtz, Maryam Karimzadehgan
NeurIPS 2023: RealML Workshop
[arXiv] [code]

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

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

We propose an optimization framework that improves the generalization of deep networks by learning more diverse representations.

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]

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]

Arguing machines: Human supervision of black box AI systems that make life-critical decisions
Lex Fridman, Li Ding, Benedikt Jenik, Bryan Reimer
CVPR 2019 Workshops
[paper] [arXiv] [video]

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

Misc.

Teaching:
TA for MIT 6.S094: Deep Learning for Self-Driving Cars (Winter 2018-19).
TA for MIT 6.S099: Artificial General Intelligence (Winter 2019).

Reviewer:
ICLR, NeurIPS, ICML, JMLR, CVPR, ICCV, ECCV, etc.

Open source projects:
google-research/ev3: Meta-learning optimization in JAX.
facebookresearch/d2go: Efficient model training and deployment on mobile platforms.
pyribs: An open-source library for quality diversity optimization.
mit-deep-learning: Tutorials and coding assignments for MIT Deep Learning courses (9k+ stars).

Side projects:

MIT 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!)

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

Last updated: 01/2026
Powered by Skeleton
Design inspired by Jon Barron