الباحثون

Weilong Yan

المنشورات 2

نسخة أولية وصول مفتوح

Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them

Hongli Xu, Weilong Yan, Anbang Wang وآخرون · 2026

Lightweight scene proxies let creators control scene layout and motion while leaving room for imagination in appearance, lighting, and visual effects. However, a suitable proxy is not uniquely defined, making paired proxy-video data difficult to construct automatically at scale. We present Proxy2World, a controllable w …

نسخة أولية وصول مفتوح

AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

Zhiyu Xu, Weilong Yan, Yufei Shi وآخرون · 2026

Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audi …

المؤلفون المشاركون