Publications (63)
Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing
Li Yang, Sen Lin, Fan Zhang +2
Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual le…
Individual solid-state nuclear spin qubits with coherence exceeding seconds
James O'Sullivan, Jaime Travesedo, Louis Pallegoix +14
The ability to coherently control and read out qubits with long coherence times in a scalable system is a crucial requirement for any quantum processor. Nuclear spins in the solid…
Electrically Programmable Pixelated Graphene-Integrated Plasmonic Metasurfaces for Coherent Mid-Infrared Emission
Xiu Liu, Yibai Zhong, Zexiao Wang +14
Active metasurfaces have recently emerged as compact, lightweight, and efficient platforms for dynamic control of electromagnetic fields and optical responses. However, the complex…
More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning
Wanhao Yu, Zheng Wang, Shuteng Niu +2
Zeroth-order (ZO) optimization has gained attention as a memory-efficient alternative to first-order (FO) methods, particularly in settings where gradient computation is expensive…
OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
Sheng Yue, Xingyuan Hua, Ju Ren +3
In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal enviro…
Generalized Image Reconstruction over T-Algebra
Liang Liao, Xuechun Zhang, Xinqiang Wang +2
Principal Component Analysis (PCA) is well known for its capability of dimension reduction and data compression. However, when using PCA for compressing/reconstructing images, imag…
GROWN: GRow Only When Necessary for Continual Learning
Li Yang, Sen Lin, Junshan Zhang +1
Catastrophic forgetting is a notorious issue in deep learning, referring to the fact that Deep Neural Networks (DNN) could forget the knowledge about earlier tasks when learning ne…
Distributed Q-Learning with State Tracking for Multi-agent Networked Control
Hang Wang, Sen Lin, Hamid Jafarkhani +1
This paper studies distributed Q-learning for Linear Quadratic Regulator (LQR) in a multi-agent network. The existing results often assume that agents can observe the global system…
Rethinking Continual Learning with Progressive Neural Collapse
Zheng Wang, Wanhao Yu, Li Yang +1
Continual Learning (CL) seeks to build an agent that can continuously learn a sequence of tasks, where a key challenge, namely Catastrophic Forgetting, persists due to the potentia…
Doubly Robust Instance-Reweighted Adversarial Training
Daouda Sow, Sen Lin, Zhangyang Wang +1
Assigning importance weights to adversarial data has achieved great success in training adversarially robust networks under limited model capacity. However, existing instance-rewei…
Outlook Towards Deployable Continual Learning for Particle Accelerators
Kishansingh Rajput, Sen Lin, Auralee Edelen +2
Particle Accelerators are high power complex machines. To ensure uninterrupted operation of these machines, thousands of pieces of equipment need to be synchronized, which requires…
Theory on Mixture-of-Experts in Continual Learning
Hongbo Li, Sen Lin, Lingjie Duan +2
Continual learning (CL) has garnered significant attention because of its ability to adapt to new tasks that arrive over time. Catastrophic forgetting (of old tasks) has been ident…
Twenty-three millisecond electron spin coherence of erbium ions in a natural-abundance crystal
Marianne Le Dantec, MiloÅ¡ RanÄiÄ, Sen Lin +12
Erbium ions doped into crystals have unique properties for quantum information processing, because of their optical transition at 1.5 m and of the large magnetic moment of thei…
Online data-driven changepoint detection for high-dimensional dynamical systems
Sen Lin, Gianmarco Mengaldo, Romit Maulik
The detection of anomalies or transitions in complex dynamical systems is of critical importance to various applications. In this study, we propose the use of machine learning to d…
Design, Control, and Applications of a Soft Robotic Arm
Hao Jiang, Zhanchi Wang, Yusong Jin +5
This paper presents the design, control, and applications of a multi-segment soft robotic arm. In order to design a soft arm with large load capacity, several design principles are…
Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code
Mahdi Kazemi, Aftab Hussain, Md Rafiqul Islam Rabin +2
This work investigates the application of Machine Unlearning (MU) for mitigating the impact of trojans embedded in conventional large language models of natural language (Text-LLMs…
Month-long-lifetime microwave spectral holes in an erbium-doped scheelite crystal at millikelvin temperature
Zhiren Wang, Sen Lin, Marianne Le Dantec +9
Rare-earth-ion (REI) ensembles in crystals have remarkable optical and spin properties characterized by narrow homogeneous linewidths relative to the inhomogeneous ensemble broaden…
Approximation of Images via Generalized Higher Order Singular Value Decomposition over Finite-dimensional Commutative Semisimple Algebra
Liang Liao, Sen Lin, Lun Li +6
Low-rank approximation of images via singular value decomposition is well-received in the era of big data. However, singular value decomposition (SVD) is only for order-two data, i…
Algorithm Design for Online Meta-Learning with Task Boundary Detection
Daouda Sow, Sen Lin, Yingbin Liang +1
Online meta-learning has recently emerged as a marriage between batch meta-learning and online learning, for achieving the capability of quick adaptation on new tasks in a lifelong…
Electron-spin spectral diffusion in an erbium doped crystal at millikelvin temperatures
Milos RanÄiÄ, Marianne Le Dantec, Sen Lin +9
Erbium-doped crystals offer a versatile platform for hybrid quantum devices because they combine magnetically-sensitive electron-spin transitions with telecom-wavelength optical tr…
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
Junze Deng, Qinhang Wu, Peizhong Ju +3
Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside…
Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence
Mehmet Dedeoglu, Sen Lin, Zhaofeng Zhang +1
Learning generative models is challenging for a network edge node with limited data and computing power. Since tasks in similar environments share model similarity, it is plausible…
Hyperspectral City V1.0 Dataset and Benchmark
Shaodi You, Erqi Huang, Shuaizhe Liang +14
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark. The documentation first starts with the background and motivation of the…
Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning
Sheng Yue, Ju Ren, Jiang Xin +2
In order to meet the requirements for performance, safety, and latency in many IoT applications, intelligent decisions must be made right here right now at the network edge. Howeve…
Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems
Hongbo Li, Qinhang Wu, Sen Lin +2
Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to spe…
Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited Communication
Sen Lin, Mehmet Dedeoglu, Junshan Zhang
Online meta-learning is emerging as an enabling technique for achieving edge intelligence in the IoT ecosystem. Nevertheless, to learn a good meta-model for within-task fast adapta…
Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback
Hang Wang, Sen Lin, Junshan Zhang
The ensemble method is a promising way to mitigate the overestimation issue in Q-learning, where multiple function approximators are used to estimate the action values. It is known…
A novel locking-free virtual element method for linear elasticity problems
Jianguo Huang, Sen Lin, Yue Yu
This paper devises a novel lowest-order conforming virtual element method (VEM) for planar linear elasticity with the pure displacement/traction boundary condition. The main trick…
Physical Vapor Deposition of High Mobility P-type Tellurium and its Applications for Gate-tunable van der Waals PN Photodiodes
Tianyi Huang, Sen Lin, Jingyi Zou +9
Recently tellurium (Te) has attracted resurgent interests due to its p-type characteristics and outstanding ambient environmental stability. Here we present a substrate engineering…
How to Leverage Diverse Demonstrations in Offline Imitation Learning
Sheng Yue, Jiani Liu, Xingyuan Hua +4
Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental probl…
Constraint-Rectified Training for Efficient Chain-of-Thought
Qinhang Wu, Sen Lin, Ming Zhang +2
Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-t…
HIPO: Instruction Hierarchy via Constrained Reinforcement Learning
Keru Chen, Jun Luo, Sen Lin +4
Hierarchical Instruction Following (HIF) refers to the problem of prompting large language models with a priority-ordered stack of instructions. Standard methods like RLHF and DPO…
Highly efficient Gauss's law-preserving spectral algorithms for Maxwell's double-curl source and eigenvalue problems based on eigen-decomposition
Sen Lin, Huiyuan Li, Zhiguo Yang
In this paper, we present Gauss's law-preserving spectral methods and their efficient solution algorithms for curl-curl source and eigenvalue problems in two and three dimensions a…
Kernelized Offline Contextual Dueling Bandits
Viraj Mehta, Ojash Neopane, Vikramjeet Das +3
Preference-based feedback is important for many applications where direct evaluation of a reward function is not feasible. A notable recent example arises in reinforcement learning…
Towards Fast Safe Online Reinforcement Learning via Policy Finetuning
Keru Chen, Honghao Wei, Zhigang Deng +1
The high costs and risks involved in extensive environment interactions hinder the practical application of current online safe reinforcement learning (RL) methods. While offline s…
Reconfigurable Ultrafast Thermal Metamaterial Pixel Arrays by Dual-Gate Graphene Transistors
Yibai Zhong, Xiu Liu, Zexiao Wang +8
Thermal signatures represent ubiquitous infrared appearances of objects, carrying their unique spectral fingerprints. Despite extensive efforts to decipher and manipulate thermal-i…
Capturing the Effects of Quantization on Trojans in Code LLMs
Aftab Hussain, Sadegh AlMahdi Kazemi Zarkouei, Md Rafiqul Islam Rabin +3
Large language models of code exhibit high capability in performing diverse software engineering tasks, such as code translation, defect detection, text-to-code generation, and cod…
A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications
Siyuan Mu, Sen Lin
Artificial intelligence (AI) has achieved astonishing successes in many domains, especially with the recent breakthroughs in the development of foundational large models. These lar…
Uncertainty Guided Online Ensemble for Non-stationary Data Streams in Fusion Science
Kishansingh Rajput, Malachi Schram, Brian Sammuli +1
Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distributi…
System Identification via Meta-Learning in Linear Time-Varying Environments
Sen Lin, Hang Wang, Junshan Zhang
System identification is a fundamental problem in reinforcement learning, control theory and signal processing, and the non-asymptotic analysis of the corresponding sample complexi…
Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation
Pei-Chi Pan, Yingbin Liang, Sen Lin
Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key m…
ChatGraph: Chat with Your Graphs
Yun Peng, Sen Lin, Qian Chen +4
Graph analysis is fundamental in real-world applications. Traditional approaches rely on SPARQL-like languages or clicking-and-dragging interfaces to interact with graph data. Howe…
Underwater Image Enhancement Based on Structure-Texture Reconstruction
Sen Lin, Kaichen Chi
Aiming at the problems of color distortion, blur and excessive noise of underwater image, an underwater image enhancement algorithm based on structure-texture reconstruction is pro…
Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
Chad Weatherly, Sen Lin
Continual anomaly detection (CAD) addresses the need for industrial inspection systems to adapt to evolving production conditions, yet existing methods share three critical gaps: u…
Non-Convex Bilevel Optimization with Time-Varying Objective Functions
Sen Lin, Daouda Sow, Kaiyi Ji +2
Bilevel optimization has become a powerful tool in a wide variety of machine learning problems. However, the current nonconvex bilevel optimization considers an offline dataset and…
MetaGater: Fast Learning of Conditional Channel Gated Networks via Federated Meta-Learning
Sen Lin, Li Yang, Zhezhi He +2
While deep learning has achieved phenomenal successes in many AI applications, its enormous model size and intensive computation requirements pose a formidable challenge to the dep…
CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning
Sheng Yue, Guanbo Wang, Wei Shao +4
This work aims to tackle a major challenge in offline Inverse Reinforcement Learning (IRL), namely the reward extrapolation error, where the learned reward function may fail to exp…
Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
Wanhao Yu, Ziyan Wang, Zheng Wang +7
Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distr…
Model-Based Offline Meta-Reinforcement Learning with Regularization
Sen Lin, Jialin Wan, Tengyu Xu +2
Existing offline reinforcement learning (RL) methods face a few major challenges, particularly the distributional shift between the learned policy and the behavior policy. Offline…
Multi-Quantile Estimators for the parameters of Generalized Extreme Value distribution
Sen Lin, Ao Kong, Robert Azencott
We introduce and study Multi-Quantile estimators for the parameters of Generalized Extreme Value (GEV) distributions to provide a robust approach to extreme value m…
DedustNet: A Frequency-dominated Swin Transformer-based Wavelet Network for Agricultural Dust Removal
Shengli Zhang, Zhiyong Tao, Sen Lin
While dust significantly affects the environmental perception of automated agricultural machines, the existing deep learning-based methods for dust removal require further research…
WaveletFormerNet: A Transformer-based Wavelet Network for Real-world Non-homogeneous and Dense Fog Removal
Shengli Zhang, Zhiyong Tao, Sen Lin
Although deep convolutional neural networks have achieved remarkable success in removing synthetic fog, it is essential to be able to process images taken in complex foggy conditio…
Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer
Sen Lin, Li Yang, Deliang Fan +1
By learning a sequence of tasks continually, an agent in continual learning (CL) can improve the learning performance of both a new task and `old' tasks by leveraging the forward k…
Instantaneous velocity during quantum tunnelling
Xiao-Wen Shang, Jian-Peng Dou, Feng Lu +3
Quantum tunnelling, a hallmark phenomenon of quantum mechanics, allows particles to pass through the classically forbidden region. It underpins fundamental processes ranging from n…
Generalization Performance of Transfer Learning: Overparameterized and Underparameterized Regimes
Peizhong Ju, Sen Lin, Mark S. Squillante +2
Transfer learning is a useful technique for achieving improved performance and reducing training costs by leveraging the knowledge gained from source tasks and applying it to targe…
Can Generalized Extreme Value Model Fit the Real Stocks
Sen Lin, Ao Kong, Robert Azencott
The Generalized Extreme Value (GEV) distribution plays a critical role in risk assessment across various domains, such as hydrology, climate science, and finance. In this study, we…
Spin coherence of near-surface ionised Te donors in silicon
Mantas Å imÄnas, James O'Sullivan, Oscar W. Kennedy +8
Impurity spins in crystal matrices are promising components in quantum technologies, particularly if they can maintain their spin properties when close to surfaces and material int…
Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning
Sen Lin, Guang Yang, Junshan Zhang
Many IoT applications at the network edge demand intelligent decisions in a real-time manner. The edge device alone, however, often cannot achieve real-time edge intelligence due t…
Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap
Hang Wang, Sen Lin, Junshan Zhang
Warm-Start reinforcement learning (RL), aided by a prior policy obtained from offline training, is emerging as a promising RL approach for practical applications. Recent empirical…
Learning from A Single Graph is All You Need for Near-Shortest Path Routing in Wireless Networks
Yung-Fu Chen, Sen Lin, Anish Arora
We propose a learning algorithm for local routing policies that needs only a few data samples obtained from a single graph while generalizing to all random graphs in a standard mod…
Knowledge-Guided Machine Learning for Stabilizing Near-Shortest Path Routing
Yung-Fu Chen, Sen Lin, Anish Arora
We propose a simple algorithm that needs only a few data samples from a single graph for learning local routing policies that generalize across a rich class of geometric random gra…
Theory on Forgetting and Generalization of Continual Learning
Sen Lin, Peizhong Ju, Yingbin Liang +1
Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL,…
TRGP: Trust Region Gradient Projection for Continual Learning
Sen Lin, Li Yang, Deliang Fan +1
Catastrophic forgetting is one of the major challenges in continual learning. To address this issue, some existing methods put restrictive constraints on the optimization space of…