5 papers
Learning-Guided Integration Contours Construction for Fast Large-Scale Generalized Eigensolvers
Yeqiu Chen, Ziyan Liu, Hong Wang +1
Solving large-scale Generalized Eigenvalue Problems (GEPs) is a fundamental yet computationally prohibitive task in science and engineering. As a promising direction, contour integ…
ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning
Yeqiu Chen, Ziyan Liu, Zhenxin Huang +3
Recent progress in LLM reasoning has increasingly shifted from single-pass generation to explicit search over intermediate reasoning states. Tree-of-Thoughts (ToT) organizes infere…
Scheduling Your LLM Reinforcement Learning with Reasoning Trees
Hong Wang, Zhezheng Hao, Jian Luo +6
Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing a query's `Reasoning Tree'. This…
Accelerating Data Generation for Nonlinear temporal PDEs via homologous perturbation in solution space
Lei Liu, Zhenxin Huang, Hong Wang +4
Data-driven deep learning methods like neural operators have advanced in solving nonlinear temporal partial differential equations (PDEs). However, these methods require large quan…
From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators
Lei Liu, Zhongyi Yu, Hong Wang +4
In recent years, Neural Operators(NO) have gradually emerged as a popular approach for solving Partial Differential Equations (PDEs). However, their application to large-scale engi…