Research can be neither truly impactful nor applicable in a vacuum. This is my "reading list"... papers I have read, am reading, or intend to read in the near future.
For a subset of those papers I have read, I've written a short blog-style post summarizing my thoughts on the paper. These posts, when they exist, are always linked underneath the title of the paper itself. Such posts are likely, but not guaranteed, to include thoughts about the paper's core contributions, potential for future research or applications, necessary considerations, and directions for future work.
Additionally, the following resources are excellent for foundational material.
Foundations of Computer Vision
A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers
Certifiably Robust Geometric Perception with Outliers
Graduated Non-Convexity for Robust Spatial Perception
Fast and Certifiable Point Cloud Registration
A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking
Global Optimality by Surfing SO(p)^n
A Certifiably Correct Algorithm for Synchronization over the Special Euclidean Group
Certifiable Estimation with Factor Graphs
Implementing Robust M-Estimators with Certifiable Factor Graph Optimization
On-Manifold Preintegration for Real-Time Visual-Inertial Odometry
Implicit Primal-Dual Interior-Point Methods for Quadratic Programming
Neural Ordinary Differential Equations
Visuomotor Policy Learning via Action Diffusion
Lyapunov-Stable Neural-Network Control
Training-Free Imitation Learning with Closed-Form Diffusion Policies
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
A Discrete Neural Sampler via Locally Equivariant Networks
An Efficient Probabilistic Hardware Architecture for Diffusion-Like Models
Energy-Efficient Codon Optimization on Thermodynamic Hardware
Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
Selective Underfitting in Diffusion Models
Shortest Paths in Graphs of Convex Sets
Regions of Attraction for Hybrid Limit Cycles of Walking Robots
A Differentiable Solver for Trajectory Optimization with Conic and Complementarity Constraints
Invariant Funnels around Trajectories using Sum-of-Squares Programming
Controls Applications of Sum-of-Squares Programming
Convex Maneuver Planning for Spacecraft Collision Avoidance
Velocity Level Approximation of Pressure Field Contact Patches
Realizing Robotic Swimming with Unified Fluid-Robot Multiphysics