الباحثون

Yuwei Hu

المنشورات 2

نسخة أولية وصول مفتوح

UniData: Universal Multimodal Instruction Generation Pipeline

Jiaqi Tang, Yi-Feng Wu, Yuting Zhang وآخرون · 2026

Multimodal Large Language Models (MLLMs) are increasingly being applied in a wider range of real-world scenarios. However, due to the substantial labor cost, creating high-quality multimodal instruction datasets for MLLMs remains a significant challenge. Although some methods propose to generate instruction data, they …

نسخة أولية وصول مفتوح

Just Align $\bm{x}$: Aligning Predictions, Not Representations

Yuyao Zhang, Yuwei Hu, Ziyang Mai وآخرون · 2026

Representation alignment has become an effective way to accelerate diffusion training, but its benefits do not transfer reliably to pixel-space clean-image prediction. In JiT, we find that auxiliary feature alignment can improve access to semantic features while reducing access to image variation needed for clean-image …

المؤلفون المشاركون