Haoxuan Li

The cost of tracking changing comparators in exp-concave online learning is reduced by a factor of $d^{1/3}$, resolving the dimension's optimal dependence.

A Unification Framework for Multimodal Data (UFMD) is introduced, which automatically processes tongue and pulse images into structured, clinically standard descriptions, integrating multi-source diagnostic information into a unified digital record of I-AOI-P process.

TCMaster is presented, a property-graph query substrate for confidence-aware traversal and workload-guided physical design over Traditional Chinese Medicine KGs, which integrates pharmacopoeias, prescriptions, molecular databases, and LLM-extracted micro-semantics into a KG with approximately 221K entities and 723K base edges.

A progressive four-stage framework that addresses three clinically critical gaps in TCM prescription generation and substantially improves prescription quality over zero-shot baselines is proposed, with a 7B model (Mistral-7B) surpassing zero-shot GPT-5 on all three TCM evaluation metrics.

Efficiently decoupling grasp synthesis from task understanding allows AdaRoboVLG to generalize across robotic hands while maintaining high performance in dynamic environments.

CogEvol slashes learning artifact generation time from minutes to seconds while ensuring high reliability and quality.