activity
20242026
collaborators

7 papers

quant-ph2026

A Global Spacetime Optimization Approach to the Real-Space Time-Dependent Schrödinger Equation

Enze Hou, Yuzhi Liu, Linxuan Zhang +3

The time-dependent Schrödinger equation (TDSE) in real space is fundamental to understanding the dynamics of many-electron quantum systems, with applications ranging from quantum…

cond-mat.mtrl-sci2026

Reinforcement Fine-Tuning for Materials Design

Zhendong Cao, Lei Wang

Reinforcement fine-tuning played an instrumental role in enhancing the instruction-following and reasoning abilities of large language models. In this work, we employ reinforcement…

physics.comp-ph2026

Multi-Task Fine-Tuning Enables Robust Out-of-Distribution Generalization in Atomistic Models

Chengqian Zhang, Duo Zhang, Anyang Peng +7

Accurate de novo molecular and materials design requires structure-property models that generalize beyond known regimes. Although pretrained atomistic models achieve strong in-dist…

cond-mat.mtrl-sci2025

CrystalFormer-CSP: Thinking Fast and Slow for Crystal Structure Prediction

Zhendong Cao, Shigang Ou, Lei Wang

Crystal structure prediction is a fundamental problem in materials science. We present CrystalFormer-CSP, an efficient framework that unifies data-driven heuristic and physics-driv…

cond-mat.mtrl-sci2025

Space Group Informed Transformer for Crystalline Materials Generation

Zhendong Cao, Xiaoshan Luo, Jian Lv +1

We introduce CrystalFormer, a transformer-based autoregressive model specifically designed for space group-controlled generation of crystalline materials. By explicitly incorporati…

cond-mat.mtrl-sci2025

CrystalFlow: A Flow-Based Generative Model for Crystalline Materials

Xiaoshan Luo, Zhenyu Wang, Qingchang Wang +4

Deep learning-based generative models have emerged as powerful tools for modeling complex data distributions and generating high-fidelity samples, offering a transformative approac…