Related papers: SPAMoE: Spectrum-Aware Hybrid Operator Framework f…
To achieve high-levels of autonomy, modern robots require the ability to detect and recover from anomalies and failures with minimal human supervision. Multi-modal sensor signals could provide more information for such anomaly detection…
Amodal segmentation targets to predict complete object masks, covering both visible and occluded regions. This task poses significant challenges due to complex occlusions and extreme shape variation, from rigid furniture to highly…
All-in-One Image Restoration (AiOIR) tasks often involve diverse degradation that require robust and versatile strategies. However, most existing approaches typically lack explicit frequency modeling and rely on fixed or heuristic…
Frequency-domain full-waveform inversion (FWI) is suitable for long-offset stationary-recording acquisition, since reliable subsurface models can be reconstructed with a few frequencies and attenuation is easily implemented without…
Neural operators have been validated as promising deep surrogate models for solving partial differential equations (PDEs). Despite the critical role of boundary conditions in PDEs, however, only a limited number of neural operators robustly…
Full waveform inversion (FWI) is a high-resolution seismic inversion technique popularly used in oil and gas exploration. Traditional FWI employs the $l_2$ norm measurement to minimize the misfit between observed and predicted seismic data.…
Mixture of Experts (MoE) architectures enable efficient scaling of neural networks but suffer from expert collapse, where routing converges to a few dominant experts. This reduces model capacity and causes catastrophic interference during…
This paper is concerned with the inverse problem of recovering the unknown signal components, along with extraction of their instantaneous frequencies (IFs), governed by the adaptive harmonic model (AHM), from discrete (and possibly…
High spatial frequency information, including fine details like textures, significantly contributes to the accuracy of semantic segmentation. However, according to the Nyquist-Shannon Sampling Theorem, high-frequency components are…
Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large…
We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer blocks. Existing tools such as $\mu$P (requires fixed architectue) or SDE (requires fixed…
Partial differential equations (PDEs) govern a wide range of physical phenomena, but their numerical solution remains computationally demanding, especially when repeated simulations are required across many parameter settings. Recent…
The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference. However, existing MoE models suffer from two…
Physics-informed neural operators have emerged as a powerful paradigm for solving parametric partial differential equations (PDEs), particularly in the aerospace field, enabling the learning of solution operators that generalize across…
A primary spectral submanifold (SSM) is the unique smoothest nonlinear continuation of a nonresonant spectral subspace $E$ of a dynamical system linearized at a fixed point. Passing from the full nonlinear dynamics to the flow on an…
We introduce a novel Multimodal Neural Operator (MNO) architecture designed to learn solution operators for multi-parameter nonlinear boundary value problems (BVPs). Traditional neural operators primarily map either the PDE coefficients or…
Mixture-of-Experts (MoE) architectures leverage sparse activation to enhance the scalability of large language models (LLMs), making them suitable for deployment in resource-constrained edge networks. However, the sheer number of experts…
Neural operators have emerged as powerful tools for learning solution operators of partial differential equations (PDEs). However, standard spectral methods based on Fourier transforms struggle with problems involving discontinuous…
Frequency-domain full-waveform inversion (FWI) is suitable for long-offset stationary-recording acquisition, since reliable subsurface models can be reconstructed with a few frequencies and attenuation is easily implemented without…
Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer…