14 papers
RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training
Binghang Lu, Yige Sun, Guang Lin
Conventional neural-network training typically follows a predefined optimization recipe, motivating a LLM agent that monitors training dynamics and adjusts optimizer settings as tr…
MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning
Lang Cao, Binghang Lu, Yuhao Shen +1
Medical question answering spans diverse specialties and modalities, and individual medical large language models (LLMs) exhibit distinct strengths across tasks and domains. This h…
CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories
Zheyuan Deng, Binghang Lu, Hanqi Feng +11
Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet…
MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations
Sky Ng, Brihi Joshi, Ishan Gupta +47
Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain i…
PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications
Yifan Simon Liu, Qianfeng Wen, Yilan Fan +40
Real user studies are important for understanding how people interact with systems under test or already deployed. In practice, however, they are often costly, time-consuming, and…
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Yikun Bai, Binghang Lu, Yikai Liu +7
Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and flow-matching models p…
fPINN-DeepONet: A Physics-Informed Operator Learning Framework for Multi-term Time-fractional Mixed Diffusion-wave Equations
Binghang Lu, Zhaopeng Hao, Christian Moya +1
In this paper, we develop a physics-informed deep operator learning framework for solving multi-term time-fractional mixed diffusion-wave equations (TFMDWEs). We begin by deriving…
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Binghang Lu, Zheyuan Deng, Runyu Zhang +6
A central challenge in continual learning for large language models (LLMs) is catastrophic forgetting, where adapting to new tasks can substantially degrade performance on previous…
AdamFLIP: Adaptive Momentum Feedback Linearization Optimization for Hard Constrained PINN Training
Binghang Lu, Runyu Zhang, Changhong Mou +2
Physics-informed neural networks (PINNs) provide a flexible framework for solving forward and inverse problems governed by partial differential equations (PDEs), but standard PINN…
Neural-POD: A Plug-and-Play Neural Operator Framework for Infinite-Dimensional Functional Nonlinear Proper Orthogonal Decomposition
Changhong Mou, Binghang Lu, Guang Lin
AI for science (AI4Science) models often suffer from discretization: learned representations remain tied to the training grid, limiting transfer across resolutions, solvers and app…
Muon with Spectral Guidance: Efficient Optimization for Scientific Machine Learning
Binghang Lu, Jiahao Zhang, Guang Lin
Physics-informed neural networks and neural operators often suffer from severe optimization difficulties caused by ill-conditioned gradients, multi-scale spectral behavior, and sti…
Morephy-Net: An Evolutionary Multi-objective Optimization for Replica-Exchange-based Physics-informed Neural Operator Learning Networks
Binghang Lu, Changhong Mou, Guang Lin
We propose an evolutionary Multi-objective Optimization for Replica-Exchange-based Physics-informed operator-learning Networks (Morephy-Net) to solve parametric partial differentia…
iPINNER: An Iterative Physics-Informed Neural Network with Ensemble Kalman Filter
Binghang Lu, Changhong Mou, Guang Lin
Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving forward and inverse problems involving partial differential equations (PDEs) by incorporating p…
NSGA-PINN: A Multi-Objective Optimization Method for Physics-Informed Neural Network Training
Binghang Lu, Christian B. Moya, Guang Lin
This paper presents NSGA-PINN, a multi-objective optimization framework for effective training of Physics-Informed Neural Networks (PINNs). The proposed framework uses the Non-domi…