Assistant Professor, Case Western Reserve University
4 papers at NeurIPS 2025
We introduce NeuralPLexer 3, a physics‑guided flow‑based generative model that delivers state‑of‑the‑art, seconds‑fast predictions of diverse biomolecular complex structures.
We introduce CaPT, leveraging both instance-aware and task-aware information for effective and efficient prompt-based learning.
uncovering the Role of Long-Context Ability in Reasoning Training
SCFG-based framework characterizes uncertainty in LLM formal reasoning, enabling selective verification that reduces errors while minimally abstaining.
