I’m Kyle Vedder

Research Interests

I believe strongly in The Bitter Lesson, and I believe our job as researchers is to find the right tricks, data distributions, and algorithms to scale up deep learning.

I believe one such trick is teaching vision systems to understand motion. My PhD research has focused on training self-supervised models to predict motion via scene flow, and building offline preprocessing pipelines to provide these motion descriptions without labels.

Academic Background

I am a CS PhD candidate at Penn under Eric Eaton and Dinesh Jayaraman in the GRASP Lab. Representative projects include:

• ZeroFlow: Scalable Scene Flow via Distillation
  • Distill an expensive optimization method into a feed-forward network and data scale it to state-of-the-art performance
• I Can’t Believe It’s Not Scene Flow!
  • Standard benchmarks were systematically broken, hiding the failure of all methods to describe small object motion; we proposed a new metric and a simple baseline that was state-of-the-art
• Argoverse 2 2024 Scene Flow Challenge
  • Hosted a challenge to push the field to close the gap between prior art and a qualitative notion of reasonable flow quality
• Neural Eulerian Scene Flow Fields
  • Fit a neural network-based scene flow volume to the entire observation and optimize it against multi-frame objectives and out pops amazing performance and emergent behaviors like point tracking.

For a narrative overview of how my PhD research fits together, see Overview of my PhD Research.

Industry / Engineering Background

I have done many industry internships:

• NVIDIA as a research intern under Zhiding Yu
• ArgoAI as a research intern under James Hays
• Amazon Lab126 as a perception intern on their home robot, Astro
• Google as a software engineering intern on adwords and ads quality
• Unidesk (a startup since aquired by Citrix)

I also have significant experience doing high-precision full stack robotics. In undergrad, I lead the greenfield development of AMRL’s Robocup Small Size League control stack and did research in multi-agent path planning.

More Information

• Email: kvedder (at) seas.upenn.edu
• Resume: /resume
• Publications: /publications
• GitHub: kylevedder
• Google Scholar: Kyle Vedder
• Twitter: KyleVedder

Updates