collaborators

8 papers

cs.LG2026

Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control

Bangyan Liao, Chenglei Yu, Yuchen Yang +4

Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained renewed interest in the machin…

cs.AI2026

BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction

Tian Xia, Tianrun Gao, Wenhao Deng +4

Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physica…

q-bio.GN2026

PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference

Chenglei Yu, Chuanrui Wang, Bangyan Liao +1

Single-cell trajectory inference from destructive time-course snapshots is fundamentally ill-posed: neither cross-time cell correspondences nor continuous trajectories are observed…

cs.LG2026

RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Data

Peiyan Hu, Haodong Feng, Hongyuan Liu +13

Predicting the evolution of complex physical systems remains a central problem in science and engineering. Despite rapid progress in scientific Machine Learning (ML) models, a crit…

q-bio.QM2026

scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction

Chenglei Yu, Chuanrui Wang, Bangyan Liao +1

A central goal in systems biology and drug discovery is to predict the transcriptional response of cells to perturbations. This task is challenging due to the noisy and sparse natu…

cs.LG2025

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration

Wenhao Deng, Long Wei, Chenglei Yu +1

Reinforcement learning with verifiable rewards (RLVR) has recently enhanced the reasoning capabilities of large language models (LLMs), particularly for mathematical problem solvin…