5 papers
Training-free Behavior Cloning
Maximilian Adang, Timothy Chen, Lars Osterberg +2
Neural behavior cloning compresses demonstrations into large models, making individual actions difficult to trace and policy updates costly. Retrieval policies retain access to dem…
UniMem: Unifying Visual and Textual Memory in VLAs for Non-Markovian Tasks
Lars Osterberg, Maggie Wang, Mac Schwager
While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-specific finetuning to achieve strong performance on long-horizon tasks, they often str…
InSight: Self-Guided Skill Acquisition via Steerable VLAs
Maggie Wang, Lars Osterberg, Stephen Tian +5
Vision-language-action (VLA) models excel at robot manipulation via imitation learning, but adapting them to new tasks often requires additional human demonstrations, which can be…
LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
Hojune Kim, Timothy Chen, Jiankai Sun +4
Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleoperation demonstrations. VLA p…
3D-architected gratings for polarization-sensitive, nature-inspired structural color
Moisés H. Ibarra Miranda, Lars W. Osterberg, Dev H. Shah +2
Structural coloration, a color-generation mechanism often found in nature, arises from light-matter interactions such as diffraction, interference and scattering, with micro- and n…