الباحثون

يوانبي تشين

المنشورات 2

نسخة أولية وصول مفتوح

KineWorld: Action-Induced Transport Fields for Embodied World Modeling

زينغ سونغ, يوشين ليو, Zhuoran Xu وآخرون · 2026

Embodied world models predict the visual consequences of candidate actions before execution. However, existing action-conditioned world models often adopt uniformly weighted visual generation objectives that can be misaligned with embodied prediction needs. Even with explicit motion conditioning, these objectives can u …

نسخة أولية وصول مفتوح

RoboFFT: Finetuning generative robot policy via online reinforcement learning with forward process

يو لي, Shenghe Hu, يوهان وانغ وآخرون · 2026

Generative models, such as diffusion and flow-based models, have shown strong promise for robot policy learning by capturing complex and multimodal action distributions from demonstrations. However, policies trained solely with imitation learning often suffer from imperfect demonstrations and distributional shifts, whi …

المؤلفون المشاركون