CV

Education

• Ph.D in Version Control Theory, GitHub University, 2018 (expected)
• M.S. in Jekyll, GitHub University, 2014
• B.S. in GitHub, GitHub University, 2012

Work experience

• Spring 2024: Academic Pages Collaborator
  • Github University
  • Duties includes: Updates and improvements to template
  • Supervisor: The Users
• Fall 2015: Research Assistant
  • Github University
  • Duties included: Merging pull requests
  • Supervisor: Professor Hub
• Summer 2015: Research Assistant
  • Github University
  • Duties included: Tagging issues
  • Supervisor: Professor Git

Skills

• Skill 1
• Skill 2
  • Sub-skill 2.1
  • Sub-skill 2.2
  • Sub-skill 2.3
• Skill 3

Publications

Standard_pub_template

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Is You Diffusion Model Actually Denoising?

A Test Function Approach to Incremental Stability

Paper Title Number 1

Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1).

On the Randomized Complexity of Minimizing a Convex Quadratic Function

Adaptive Sampling for Convex Regression

On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation

PhD Thesis: Statistical Complexity and Regret in Linear Control

The Pitfalls of Imitation Learning when Actions are Continuous

History-Guided Video Diffusion

Diffusion Policy Policy Optimization

Self-Improvement in Language Models: The Sharpening Mechanism

Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans?

Non-Euclidean Motion Planning with Graphs of Geodesically-Convex Sets

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Faster Algorithms for Growing Collision-Free Convex Polytopes in Robot Configuration Space

Constrained Bimanual Planning with Analytic Inverse Kinematics

Fleet Policy Learning via Weight Merging and An Application to Robotic Tool-Use

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Paper Title Number 4

Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Smoothed Online Learning for Prediction in Piecewise Affine Systems

Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior

Exploration and Incentives in Reinforcement Learning

Non-Euclidean Motion Planning with Graphs of Geodesically-Convex Sets

The Power of Learned Locally Linear Models for Nonlinear Policy Optimization

Imitating Complex Trajectories: Bridging Low-Level Stability and High-Level Behavior

Statistical Learning under Heterogenous Distribution Shift

Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making

Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective

Learning to Extrapolate: A Transductive Approach

Pathologies and Challenges of Using Differentiable Simulators in Policy Optimization for Contact-Rich Manipulation

Learning to Extrapolate: A Transductive Approach

Globally Convergent Policy Search over Dynamic Filters for Output Estimation

Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions

Do Differentiable Simulators Give Better Policy Gradients?

Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes

First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach

Beyond No Regret: Instance-Dependent PAC Reinforcement Learning

Online Control of Unknown Time-Varying Dynamical Systems

Stabilizing Dynamical Systems via Policy Gradient Methods

Bayesian decision-making under misspecified priors with applications to meta-learning

On Stability of Nonlinear Receding Horizon Control: A Geometric Perspective

Task-Optimal Exploration in Linear Dynamical Systems

Corruption Robust Exploration in Episodic Reinforcement Learning

Towards a Dimension-Free Understanding of Adaptive Linear Control

Learning a Linear Quadratic Regular from Nonlinear Observations

Making Non-Stochastic Control (Almost) as Easy as Stochastic

Constrained episodic reinforcement learning in concave-convex and knapsack settings

Reward-Free Exploration for Reinforcement Learning

Naive Exploration is Optimal for Online LQR

Logarithmic Regret for Online Control with Adversarial Disturbances

Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning

Improper Learning for Nonstochastic Control

The gradient complexity of linear regression

A Successive-Elimination Approach to Adaptive Robotic Source Seeking

First-order Methods Almost Always Avoid Saddle Points

Learning Linear Dynamical Systems with Semi-Parametric Least Squares

The Implicit Fairness Criterion of Unconstrained Learning

Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs”

First-order Methods Almost Always Avoid Saddle Points

Balancing Competing Objectives for Welfare-Aware Machine Learning with Imperfect Data

Approximate Ranking from Pairwise Comparisons

Tight Query Complexity Lower Bounds for PCA via Finite Sample Deformed Wigner Law

Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification

Delayed Impact of Fair Machine Learning

The Simulator: Towards a Richer Understanding of Adaptive Sampling in the Moderate-Confidence Regime

Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

Gradient Descent Converges to Minimizers

Best-of-K Bandits

Paper Shit Number 4

Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).

Paper Title Number 3

Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3).

Paper Title Number 2

Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2).

Talks

Tutorial: Nonstochastic Control

December 10, 2025

Tutorial at Conference on Decision and Control, Rio de Janeiro, Brazil

Tutorial: Foundations of Imitation Learning: From Language Modeling to Continuous Control

December 05, 2025

Tutorial at NeurIPS, San Diego, CA

Why We Chunk Our Actions (and other curiosities of modern robot learning)

September 27, 2025

Talk at CoRL 2025 Workshop on Making Sense of Data in Robotics, Seoul, South Korea

Why AI is Harder in the Physical World (and what to maybe do about it)

July 21, 2025

Talk at SFU@ICML Workshop, July 2025, Vancouver, BC, Canada

The Pitfalls of Imitation Learning when Actions are Continuous

April 29, 2025

Talk at RL Theory Virtual Seminar, Virtual

Teaching

Convex Optimization and Approximation

Introduction to Machine Learning

Teaching experience 2

Teaching experience 1

Service and leadership

• Currently signed in to 43 different slack teams