Search Results for author: Lu Lu

Found 57 papers, 24 papers with code

Inclusion in CSR Reports: The Lens from a Data-Driven Machine Learning Model

no code implementations CSRNLP (LREC) 2022 Lu Lu, Jinghang Gu, Chu-Ren Huang

Inclusion, as one of the foundations in the diversity, equity, and inclusion initiative, concerns the degree of being treated as an ingroup member in a workplace.

Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks

no code implementations23 Feb 2024 Christian Moya, Amirhossein Mollaali, Zecheng Zhang, Lu Lu, Guang Lin

In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regression.

Conformal Prediction Prediction Intervals +2

DIMON: Learning Solution Operators of Partial Differential Equations on a Diffeomorphic Family of Domains

no code implementations11 Feb 2024 Minglang Yin, Nicolas Charon, Ryan Brody, Lu Lu, Natalia Trayanova, Mauro Maggioni

DIMON is based on transporting a given problem (initial/boundary conditions and domain $\Omega_{\theta}$) to a problem on a reference domain $\Omega_{0}$, where training data from multiple problems is used to learn the map to the solution on $\Omega_{0}$, which is then re-mapped to the original domain $\Omega_{\theta}$.

Operator learning

Challenges in Training PINNs: A Loss Landscape Perspective

no code implementations2 Feb 2024 Pratik Rathore, Weimu Lei, Zachary Frangella, Lu Lu, Madeleine Udell

This paper explores challenges in training Physics-Informed Neural Networks (PINNs), emphasizing the role of the loss landscape in the training process.

Speeding up and reducing memory usage for scientific machine learning via mixed precision

no code implementations30 Jan 2024 Joel Hayford, Jacob Goldman-Wetzler, Eric Wang, Lu Lu

Scientific machine learning (SciML) has emerged as a versatile approach to address complex computational science and engineering problems.

Computational Efficiency

CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing

no code implementations22 Jan 2024 Xianghu Yue, Xiaohai Tian, Lu Lu, Malu Zhang, Zhizheng Wu, Haizhou Li

To bridge the gap between modalities, CoAVT employs a query encoder, which contains a set of learnable query embeddings, and extracts the most informative audiovisual features of the corresponding text.

AudioCaps Audio-Visual Synchronization +4

Planning Reliability Assurance Tests for Autonomous Vehicles

no code implementations30 Nov 2023 Simin Zheng, Lu Lu, Yili Hong, Jian Liu

This paper aims to fill in this gap by developing statistical methods for planning AV reliability assurance tests based on recurrent events data.

Autonomous Vehicles

Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer

no code implementations15 Nov 2023 Jin Qiu, Lu Huang, Boyu Li, Jun Zhang, Lu Lu, Zejun Ma

Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

ROAM: memory-efficient large DNN training via optimized operator ordering and memory layout

no code implementations30 Oct 2023 Huiyao Shu, Ang Wang, Ziji Shi, Hanyu Zhao, Yong Li, Lu Lu

However, a memory-efficient execution plan that includes a reasonable operator execution order and tensor memory layout can significantly increase the models' memory efficiency and reduce overheads from high-level techniques.

D2NO: Efficient Handling of Heterogeneous Input Function Spaces with Distributed Deep Neural Operators

no code implementations29 Oct 2023 Zecheng Zhang, Christian Moya, Lu Lu, Guang Lin, Hayden Schaeffer

Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems.

SALMONN: Towards Generic Hearing Abilities for Large Language Models

1 code implementation20 Oct 2023 Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, Chao Zhang

Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of at least three types of sounds: speech, audio events, and music.

Audio captioning Automatic Speech Recognition +10

Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models

2 code implementations9 Oct 2023 Guangzhi Sun, Wenyi Yu, Changli Tang, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, Chao Zhang

Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs.

Question Answering Video Question Answering

Connecting Speech Encoder and Large Language Model for ASR

no code implementations25 Sep 2023 Wenyi Yu, Changli Tang, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, Chao Zhang

Q-Former-based LLMs can generalise well to out-of-domain datasets, where 12% relative WER reductions over the Whisper baseline ASR model were achieved on the Eval2000 test set without using any in-domain training data from Switchboard.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

LLM-Mini-CEX: Automatic Evaluation of Large Language Model for Diagnostic Conversation

no code implementations15 Aug 2023 Xiaoming Shi, Jie Xu, Jinru Ding, Jiali Pang, Sichen Liu, Shuqing Luo, Xingwei Peng, Lu Lu, Haihong Yang, Mingtao Hu, Tong Ruan, Shaoting Zhang

Despite their alluring technological potential, there is no unified and comprehensive evaluation criterion, leading to the inability to evaluate the quality and potential risks of medical LLMs, further hindering the application of LLMs in medical treatment scenarios.

Language Modelling Large Language Model +1

Learning Specialized Activation Functions for Physics-informed Neural Networks

1 code implementation8 Aug 2023 Honghui Wang, Lu Lu, Shiji Song, Gao Huang

To avoid the inefficient manual selection and to alleviate the optimization difficulty of PINNs, we introduce adaptive activation functions to search for the optimal function when solving different problems.

PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs

1 code implementation15 Jun 2023 Zhongkai Hao, Jiachen Yao, Chang Su, Hang Su, Ziao Wang, Fanzhi Lu, Zeyu Xia, Yichi Zhang, Songming Liu, Lu Lu, Jun Zhu

In addition to providing a standardized means of assessing performance, PINNacle also offers an in-depth analysis to guide future research, particularly in areas such as domain decomposition methods and loss reweighting for handling multi-scale problems and complex geometry.


Towards Building Voice-based Conversational Recommender Systems: Datasets, Potential Solutions, and Prospects

1 code implementation14 Jun 2023 Xinghua Qu, Hongyang Liu, Zhu Sun, Xiang Yin, Yew Soon Ong, Lu Lu, Zejun Ma

Conversational recommender systems (CRSs) have become crucial emerging research topics in the field of RSs, thanks to their natural advantages of explicitly acquiring user preferences via interactive conversations and revealing the reasons behind recommendations.

Recommendation Systems

CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training

no code implementations27 May 2023 Linhao Dong, Zhecheng An, Peihao Wu, Jun Zhang, Lu Lu, Zejun Ma

We also observe the cross-modal representation extracted by CIF-PT obtains better performance than other neural interfaces for the tasks of SLU, including the dominant speech representation learned from self-supervised pre-training.

intent-classification Intent Classification +5

Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness

1 code implementation26 May 2023 Min Zhu, Shihang Feng, Youzuo Lin, Lu Lu

Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources.

Computational Efficiency

PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systems

1 code implementation18 May 2023 Shunyuan Mao, Ruobing Dong, Lu Lu, Kwang Moo Yi, Sifan Wang, Paris Perdikaris

We develop a tool, which we name Protoplanetary Disk Operator Network (PPDONet), that can predict the solution of disk-planet interactions in protoplanetary disks in real-time.

Deep Learning for Solving and Estimating Dynamic Macro-Finance Models

no code implementations5 May 2023 Benjamin Fan, Edward Qiao, Anran Jiao, Zhouzhou Gu, Wenhao Li, Lu Lu

We develop a methodology that utilizes deep learning to simultaneously solve and estimate canonical continuous-time general equilibrium models in financial economics.

Enhancing Large Language Model with Self-Controlled Memory Framework

1 code implementation26 Apr 2023 Bing Wang, Xinnian Liang, Jian Yang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.

Book summarization Document Summarization +5

Robust Andrew's sine estimate adaptive filtering

no code implementations29 Mar 2023 Lu Lu, Yi Yu, Zongsheng Zheng, Guangya Zhu, Xiaomin Yang

Two Andrew's sine estimator (ASE)-based robust adaptive filtering algorithms are proposed in this brief.


Fourier-MIONet: Fourier-enhanced multiple-input neural operators for multiphase modeling of geological carbon sequestration

1 code implementation8 Mar 2023 Zhongyi Jiang, Min Zhu, Dongzhuo Li, Qiuzi Li, Yanhua O. Yuan, Lu Lu

Here, we develop a Fourier-enhanced multiple-input neural operator (Fourier-MIONet) to learn the solution operator of the problem of multiphase flow in porous media.

Reliable extrapolation of deep neural operators informed by physics or sparse observations

1 code implementation13 Dec 2022 Min Zhu, Handi Zhang, Anran Jiao, George Em Karniadakis, Lu Lu

Deep neural operators can learn nonlinear mappings between infinite-dimensional function spaces via deep neural networks.

Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition

no code implementations28 Oct 2022 Yist Y. Lin, Tao Han, HaiHua Xu, Van Tung Pham, Yerbolat Khassanov, Tze Yuang Chong, Yi He, Lu Lu, Zejun Ma

One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched.

Action Detection Activity Detection +4

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

2 code implementations21 Jul 2022 Chenxi Wu, Min Zhu, Qinyang Tan, Yadhu Kartha, Lu Lu

Hence, we have considered a total of 10 different sampling methods, including six non-adaptive uniform sampling, uniform sampling with resampling, two proposed adaptive sampling, and an existing adaptive sampling.

Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics

1 code implementation9 May 2022 Xin-Yang Liu, Min Zhu, Lu Lu, Hao Sun, Jian-Xun Wang

Traditional data-driven deep learning models often struggle with high training costs, error accumulation, and poor generalizability in complex physical processes.

Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport

2 code implementations14 Apr 2022 Lu Lu, Raphael Pestourie, Steven G. Johnson, Giuseppe Romano

Deep neural operators can learn operators mapping between infinite-dimensional function spaces via deep neural networks and have become an emerging paradigm of scientific machine learning.

Conjugate Gradient Adaptive Learning with Tukey's Biweight M-Estimate

no code implementations19 Mar 2022 Lu Lu, Yi Yu, Rodrigo C. de Lamare, Xiaomin Yang

We propose a novel M-estimate conjugate gradient (CG) algorithm, termed Tukey's biweight M-estimate CG (TbMCG), for system identification in impulsive noise environments.

MIONet: Learning multiple-input operators via tensor product

2 code implementations12 Feb 2022 Pengzhan Jin, Shuai Meng, Lu Lu

Based on our theory and a low-rank approximation, we propose a novel neural operator, MIONet, to learn multiple-input operators.

Systems Biology: Identifiability analysis and parameter identification via systems-biology informed neural networks

2 code implementations3 Feb 2022 Mitchell Daneker, Zhen Zhang, George Em Karniadakis, Lu Lu

The dynamics of systems biological processes are usually modeled by a system of ordinary differential equations (ODEs) with many unknown parameters that need to be inferred from noisy and sparse measurements.

Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems

2 code implementations1 Nov 2021 Jeremy Yu, Lu Lu, Xuhui Meng, George Em Karniadakis

We tested gPINNs extensively and demonstrated the effectiveness of gPINNs in both forward and inverse PDE problems.

Active noise control techniques for nonlinear systems

no code implementations19 Oct 2021 Lu Lu, Kai-Li Yin, Rodrigo C. de Lamare, Zongsheng Zheng, Yi Yu, Xiaomin Yang, Badong Chen

Most of the literature focuses on the development of the linear active noise control (ANC) techniques.

A survey on active noise control techniques -- Part I: Linear systems

no code implementations1 Oct 2021 Lu Lu, Kai-Li Yin, Rodrigo C. de Lamare, Zongsheng Zheng, Yi Yu, Xiaomin Yang, Badong Chen

Active noise control (ANC) is an effective way for reducing the noise level in electroacoustic or electromechanical systems.

Study of Proximal Normalized Subband Adaptive Algorithm for Acoustic Echo Cancellation

no code implementations14 Aug 2021 Gang Guo, Yi Yu, Rodrigo C. de Lamare, Zongsheng Zheng, Lu Lu, Qiangming Cai

In addition, an adaptive approach for the choice of the thresholding parameter in the proximal step is also proposed based on the minimization of the mean square deviation.

Acoustic echo cancellation

One-shot learning for solution operators of partial differential equations

no code implementations6 Apr 2021 Anran Jiao, Haiyang He, Rishikesh Ranade, Jay Pathak, Lu Lu

Discovering governing equations of a physical system, represented by partial differential equations (PDEs), from data is a central challenge in a variety of areas of science and engineering.

One-Shot Learning Operator learning

Physics-informed neural networks with hard constraints for inverse design

4 code implementations9 Feb 2021 Lu Lu, Raphael Pestourie, Wenjie Yao, Zhicheng Wang, Francesc Verdugo, Steven G. Johnson

We achieve the same objective as conventional PDE-constrained optimization methods based on adjoint methods and numerical PDE solvers, but find that the design obtained from hPINN is often simpler and smoother for problems whose solution is not unique.

Mixed graphs with smallest eigenvalue greater than $-\frac{\sqrt{5}+1}{2}$

no code implementations24 Dec 2020 Lu Lu, ZhenZhen Lou

The classical problem of characterizing the graphs with bounded eigenvalues may date back to the work of Smith in 1970.

Combinatorics 05C50

Operator learning for predicting multiscale bubble growth dynamics

no code implementations23 Dec 2020 Chensen Lin, Zhen Li, Lu Lu, Shengze Cai, Martin Maxey, George Em Karniadakis

Simulating and predicting multiscale problems that couple multiple physics and dynamics across many orders of spatiotemporal scales is a great challenge that has not been investigated systematically by deep neural networks (DNNs).

Computational Physics

Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition

no code implementations26 Aug 2020 Ping Liu, Yuewei Lin, Zibo Meng, Lu Lu, Weihong Deng, Joey Tianyi Zhou, Yi Yang

In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.

Adversarial Attack Data Augmentation +4

Physics-informed neural networks for inverse problems in nano-optics and metamaterials

1 code implementation2 Dec 2019 Yuyao Chen, Lu Lu, George Em. Karniadakis, Luca Dal Negro

In this paper we employ the emerging paradigm of physics-informed neural networks (PINNs) for the solution of representative inverse scattering problems in photonic metamaterials and nano-optics technologies.

Computational Physics Optics

DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

4 code implementations8 Oct 2019 Lu Lu, Pengzhan Jin, George Em. Karniadakis

This universal approximation theorem is suggestive of the potential application of neural networks in learning nonlinear operators from data.

DeepXDE: A deep learning library for solving differential equations

6 code implementations10 Jul 2019 Lu Lu, Xuhui Meng, Zhiping Mao, George E. Karniadakis

We also present a Python library for PINNs, DeepXDE, which is designed to serve both as an education tool to be used in the classroom as well as a research tool for solving problems in computational science and engineering.

Gated Multiple Feedback Network for Image Super-Resolution

1 code implementation9 Jul 2019 Qilei Li, Zhen Li, Lu Lu, Gwanggil Jeon, Kai Liu, Xiaomin Yang

The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era.

Image Super-Resolution

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

1 code implementation27 May 2019 Pengzhan Jin, Lu Lu, Yifa Tang, George Em. Karniadakis

To derive a meaningful bound, we study the generalization error of neural networks for classification problems in terms of data distribution and neural network smoothness.

Dying ReLU and Initialization: Theory and Numerical Examples

no code implementations15 Mar 2019 Lu Lu, Yeonjong Shin, Yanhui Su, George Em. Karniadakis

Numerical examples are provided to demonstrate the effectiveness of the new initialization procedure.

How to Host a Data Competition: Statistical Advice for Design and Analysis of a Data Competition

no code implementations16 Jan 2019 Christine M. Anderson-Cook, Kary L. Myers, Lu Lu, Michael L. Fugate, Kevin R. Quinlan, Norma Pawley

It also describes a post-competition analysis that enables robust and efficient assessment of the strengths and weaknesses of solutions from different competitors, as well as greater understanding of the regions of the input space that are well-solved.

Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems

no code implementations21 Sep 2018 Dongkun Zhang, Lu Lu, Ling Guo, George Em. Karniadakis

Here, we propose a new method with the objective of endowing the DNN with uncertainty quantification for both sources of uncertainty, i. e., the parametric uncertainty and the approximation uncertainty.

Active Learning Uncertainty Quantification

Collapse of Deep and Narrow Neural Nets

1 code implementation ICLR 2019 Lu Lu, Yanhui Su, George Em. Karniadakis

However, here we show that even for such activation, deep and narrow neural networks (NNs) will converge to erroneous mean or median states of the target function depending on the loss with high probability.

Cannot find the paper you are looking for? You can Submit a new open access paper.