Wuyang Chen

Verifiable PDE Reasoning and Modeling with Neurosymbolics

Wuyang Chen

Recent progress in Large Language Models (LLMs) has transformed text and code generation, yet models still falter on Partial Differential Equations (PDEs) where correctness, constraints, and physical consequences are critical. We explore how formal LLM reasoning can advance symbolic PDE modeling. First, …

ca (code pays fourni par la source)

Delegation in Need is not Effective Indeed: A Contingent Model of Leader Ego Depletion and LMX

Su Qin, Erzhuo Wang, Wuyang Chen

Effective delegation behavior is believed to benefit both leaders and followers, as it frees leaders from active supervisory roles and develops followers with more opportunities. However, empirical studies have produced mixed findings regarding when and how to delegate. To develop a more …

cn, hk (code pays fourni par la source)

Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search

Jialin Lu, Soonho Kong, Rodrigo Stehling, Kaiyu Yang et autres

We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across library versions, yet existing refactoring works overlook three practical challenges: 1) Lean refactoring is natively multi-objective …

Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search

Jialin Lu, Soonho Kong, Rodrigo Stehling, Kaiyu Yang et autres

We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across library versions, yet existing refactoring works overlook three practical challenges: 1) Lean refactoring is natively multi-objective …

us (code pays fourni par la source)

FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction

Yuqiu Liu, Jialin Song, Marissa Ramirez de Chanlatte, Rochishnu Chowdhury et autres

Real objects that inhabit the physical world follow physical laws and thus behave plausibly during interaction with other physical objects. However, current methods that perform 3D reconstructions of real-world scenes from multi-view 2D images optimize primarily for visual fidelity, i.e., they train …

us (code pays fourni par la source)

Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model

Yuqiu Liu, Jingxuan Xu, Mauricio Soroco, Yunchao Wei et autres

Recent developments in 3D vision have enabled significant progress in inferring neural fluid fields and realistic rendering of fluid dynamics. However, these methods require dense captures of real-world flow, which demand specialized lab setups, making the process costly and challenging. Scientific machine …

ca, cn (code pays fourni par la source)

System-level multi-stage modeling and multi-criteria optimization of direct ink writing

Wuyang Chen, Chenyu Xu, L.H. Liang, Chi Zhou et autres

Direct ink writing (DIW) has emerged as an additive manufacturing technique for fabricating multiple functional structures, but its deployment is often limited by stage-wise optimization that overlooks system-level trade-offs among printability, structural integrity, and energy efficiency. To address this gap, we develop …

us (code pays fourni par la source)

Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge

Siying Ma, Mehrdad M. Zadeh, Mauricio Soroco, Wuyang Chen et autres

Recent advances in scientific machine learning (SciML) have enabled neural operators (NOs) to serve as powerful surrogates for modeling the dynamic evolution of physical systems governed by partial differential equations (PDEs). While existing approaches focus primarily on learning simulations from the target …

Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge

Siying Ma, Mehrdad M. Zadeh, Mauricio Soroco, Wuyang Chen et autres

Recent advances in scientific machine learning (SciML) have enabled neural operators (NOs) to serve as powerful surrogates for modeling the dynamic evolution of physical systems governed by partial differential equations (PDEs). While existing approaches focus primarily on learning simulations from the target …

Underwater Acoustics

Boqing Zhu, Qisheng Xu, Yi Su, Qian Zhu et autres

cn (code pays fourni par la source)

Wave energy assessments around Hainan Island based on a fine-resolution model: the long-term trend and climatic mutation

Junmin Li, Shaotian Li, Wuyang Chen, Yineng Li et autres

cn (code pays fourni par la source)

The climatic mutation in the long-term trends of wind and wave energies in the south China sea

Weiyi Sun, Junmin Li, Wuyang Chen, Yineng Li et autres

cn (code pays fourni par la source)