الباحثون

Haruki Nishimura

المنشورات 2

نسخة أولية وصول مفتوح

Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor Imitation

Wonsuhk Jung, Sundhar Vinodh Sangeetha, Chen Xu وآخرون · 2026

Goal-conditioned imitation learning (GCIL) with flow matching is a promising framework that can represent multimodal behaviors while adapting to diverse, user-specified goals, yet often fails when goals lie outside the demonstration support. To extrapolate to such unseen goals without collapsing multimodality - a probl …

نسخة أولية وصول مفتوح

The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models

Chen Xu, Rishi Shah, Hadas Kress-Gazit وآخرون · 2026

Modern robot imitation learning increasingly relies on generative policies based on diffusion or flow-matching models, which generate actions by transforming samples from a prior distribution. A key question is whether the choice of prior matters. Replacing the standard Gaussian with a closer-to-target, non-Gaussian pr …

المؤلفون المشاركون