OSعُمان للعلوم
الباحثون

Canran Xiao

المنشورات 2

نسخة أولية وصول مفتوح

Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution

Siyuan Ma, Canran Xiao, Zikai Xiao وآخرون · 2026

Model-guided directed evolution seeks to identify high-fitness protein variants under limited oracle budgets. Protein language models (PLMs) provide rich representations for this task, but task-agnostic zero-shot scores can be misaligned with a target assay, while supervised search in high-dimensional embedding spaces …

نسخة أولية وصول مفتوح

MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models

Yanshu Li, Jiaqian Li, Canran Xiao وآخرون · 2026

Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as model size decreases. Knowledge distillation offers a natural way to bridge this gap, but existing methods primarily align output distributions or hidden representations dire …

المؤلفون المشاركون

Siyuan MaZikai XiaoAlbert GaoLiang HeXuan-Yu WangShuying CaoXiaojun JiaYanshu LiJiaqian LiXi XiaoTianyang WangYongtai Liu