5 papers
ESP: Energy-Score Policy for One-Step Multimodal Action Generation
Lilika Makabe, Heecheol Kim, Yasuyuki Matsushita
Generative action models based on diffusion and flow matching have been increasingly adopted in vision-language-action (VLA) policies for their ability to capture diverse behaviors…
VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
Namiko Saito, Kinam Kim, Heecheol Kim +2
Vision-language-action (VLA) models provide broad, instruction-conditioned manipulation behaviors, but their physical execution can remain imprecise during contact-rich interaction…
ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration
Heecheol Kim, Namiko Saito, Katsushi Ikeuchi +1
Sim-to-real policy transfer -- deploying policies trained in simulation in the real world -- is a promising paradigm for scaling robot manipulation without large-scale real-world d…
Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement
Kinam Kim, Namiko Saito, Heecheol Kim +3
Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions du…
Shadow Art Kanji: Inverse Rendering Application
William Louis Rothman, Yasuyuki Matsushita
Finding a balance between artistic beauty and machine-generated imagery is always a difficult task. This project seeks to create 3D models that, when illuminated, cast shadows rese…