3 citations · 5 across the 17 of their papers we have counts for
18 papers
Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control
Christian Moya, Elliott Thornley, Guang Lin
In reinforcement learning with verifiable rewards (RLVR), imperfect verifiers can reward incorrect responses, creating opportunities for reward hacking. Using gradient flow with a…
A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients
Haoguang Wang, Huy Hoang Le, Akhila Kandivalasa +3
This paper proposes a Mamba surrogate model with mixture-of-experts (MoE) routing to represent the transient dynamics of inverter-based resources. A Mamba surrogate model is a pred…
GraspMeanFlow: SE(3)-Equivariant MeanFlow for Few-Step 6-DoF Grasp Generation
Jiyong Kwon, Yikun Bai, Amirhossein Mollaali +1
Recent data-driven methods for synthesizing 6-DoF grasp poses use generative models to learn complex grasp pose distributions and generate diverse candidate poses. In particular, S…
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
Christian Moya, Alex Semendinger, Guang Lin +1
Preference learning methods like Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy and length bias in today's langua…
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…
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
Wei-Ping Huang, Chee-En Yu, Guan-Ting Lin +1
Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoreticall…
Conformalized Quantum DeepONet Ensembles: Towards Scalable Operator Learning with Distribution-Free Guarantees
Purav Matlia, Christian Moya, Guang Lin
Operator learning enables fast surrogate modelling of high-dimensional dynamical systems, but existing approaches face two fundamental limitations: the quadratic cost of dense neur…
Physics-Guided Dimension Reduction for Simulation-Free Operator Learning of Stiff Differential-Algebraic Systems
Huy Hoang Le, Haoguang Wang, Christian Moya +2
Neural surrogates for stiff differential-algebraic equations (DAEs) face two barriers: soft-constraint methods leave algebraic residuals that stiffness amplifies into errors, and h…
DiLO: Decoupling Generative Priors and Neural Operators via Diffusion Latent Optimization for Inverse Problems
Haibo Liu, Guang Lin
Diffusion models have emerged as powerful generative priors for solving PDE-constrained inverse problems. Compared with end-to-end approaches that learn inverse mappings from large…
Jeffreys Flow: Robust Boltzmann Generators for Rare Event Sampling via Parallel Tempering Distillation
Guang Lin, Christian Moya, Di Qi +1
Sampling physical systems with rough energy landscapes is hindered by rare events and metastable trapping. While Boltzmann generators already offer a solution, their reliance on th…
pADAM: A Plug-and-Play All-in-One Diffusion Architecture for Multi-Physics Learning
Amirhossein Mollaali, Bongseok Kim, Christian Moya +1
Generalizing across disparate physical laws remains a fundamental challenge for artificial intelligence in science. Existing deep-learning solvers are largely confined to single-eq…
Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning
Amirhossein Mollaali, Christian Bolivar Moya, Amanda A. Howard +3
This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov-Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure…
Conformalized Prediction of Post-Fault Voltage Trajectories Using Pre-trained and Finetuned Attention-Driven Neural Operators
Amirhossein Mollaali, Gabriel Zufferey, Gonzalo Constante-Flores +4
This paper proposes a new data-driven methodology for predicting intervals of post-fault voltage trajectories in power systems. We begin by introducing the Quantile Attention-Fouri…
Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks
Christian Moya, Amirhossein Mollaali, Zecheng Zhang +2
In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for…
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
Haoyang Zheng, Wei Deng, Christian Moya +1
Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounter…
B-LSTM-MIONet: Bayesian LSTM-based Neural Operators for Learning the Response of Complex Dynamical Systems to Length-Variant Multiple Input Functions
Zhihao Kong, Amirhossein Mollaali, Christian Moya +2
Deep Operator Network (DeepONet) is a neural network framework for learning nonlinear operators such as those from ordinary differential equations (ODEs) describing complex systems…
A Physics-Guided Bi-Fidelity Fourier-Featured Operator Learning Framework for Predicting Time Evolution of Drag and Lift Coefficients
Amirhossein Mollaali, Izzet Sahin, Iqrar Raza +3
In the pursuit of accurate experimental and computational data while minimizing effort, there is a constant need for high-fidelity results. However, achieving such results often re…