4 papers
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Alberta Longhini, David Emukpere, Jean-Michel Renders +1
We address the problem of fine-tuning pre-trained generative policies with reinforcement learning (RL) while preserving the multimodality of their action distributions. Existing me…
Robust Skills, Brittle Grounding: Diagnosing Restricted Generalization in Vision-Language Action Policies via Multi-Object Picking
David Emukpere, Romain Deffayet, Jean-Michel Renders
Vision-language action (VLA) policies often report strong manipulation benchmark performance with relatively few demonstrations, but it remains unclear whether this reflects robust…
Disentangled Object-Centric Image Representation for Robotic Manipulation
David Emukpere, Romain Deffayet, Bingbing Wu +6
Learning robotic manipulation skills from vision is a promising approach for developing robotics applications that can generalize broadly to real-world scenarios. As such, many app…
SLIM: Skill Learning with Multiple Critics
David Emukpere, Bingbing Wu, Julien Perez +1
Self-supervised skill learning aims to acquire useful behaviors that leverage the underlying dynamics of the environment. Latent variable models, based on mutual information maximi…