University of Washington

“we annotate the DROID dataset with progress-rewards obtained from Robometer (reduced by 1 to get negative rewards)... reward supervision from RoboMeter can be noisy, motivating the development of better reward models for failure prediction”

“She does her 'very best not to read any synthetic text' but 'oftentimes people will send me something and I won't know.'”

“Many people who later made comparatively large contributions in LLM and agent research actually came from semantic parsing backgrounds — like Percy Liang at Stanford, Luke Zettlemoyer at University of Washington...”