Jeremy Morgan
Jeremy Morgan is a PhD candidate in the Department of Computer Science at the University of Southern California, where he is affiliated with the Robotic Embedded Systems Lab. His research focuses on robotic manipulation, inverse kinematics, and benchmarking generalization for vision-language-action models. He is a co-author of Colosseum V2, a benchmark for evaluating VLA model generalization, as well as IKFlow and CppFlow, methods for generating diverse inverse kinematics solutions.
“Colosseum V2: Benchmarking Generalization for Vision Language Action Models”
Source→“the sim-to-real validation shows an average R² of 0.798 for predicting perturbation-induced success rate changes and a Spearman correlation of 0.916 for rank-ordering perturbation difficulty.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.