papers

Publications (63)

cs.CV2023

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…

quant-ph2024

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…

physics.optics2024

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…

cs.LG2026

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…

cs.LG2024

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…

cs.CV2021

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…

cs.LG2021

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…

cs.MA2020

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…

cs.LG2026

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…

cs.LG2023

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…

cs.LG2025

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…

cs.LG2025

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…

quant-ph2021

Twenty-three millisecond electron spin coherence of erbium ions in a natural-abundance crystal

Marianne Le Dantec, Miloš Rančić, 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…

math.DS2023

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…

cs.RO2020

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…

cs.SE2024

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…

quant-ph2024

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…

cs.LG2022

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…

cs.LG2024

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…

quant-ph2022

Electron-spin spectral diffusion in an erbium doped crystal at millikelvin temperatures

Milos Rančić, 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…

cs.LG2025

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…

cs.LG2021

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…

cs.CV2020

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…

cs.LG2021

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…

cs.LG2025

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…

cs.LG2020

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…

cs.LG2023

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…

math.NA2022

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…

physics.app-ph2024

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…

cs.LG2024

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…

cs.LG2026

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…

cs.LG2026

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…

math.NA2024

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…

cs.LG2023

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…

cs.LG2026

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…

physics.optics2025

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…

cs.SE2025

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2020

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…

cs.LG2026

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…

cs.AI2024

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…

eess.IV2020

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…

cs.LG2026

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…

math.OC2023

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…

cs.LG2020

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…

cs.LG2023

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…

cs.LG2026

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…

cs.LG2022

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…

stat.ME2025

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…

cs.CV2024

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…

cs.CV2024

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…

cs.LG2022

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…

quant-ph2025

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…

cs.LG2023

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…

stat.AP2024

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…

cond-mat.mes-hall2022

Spin coherence of near-surface ionised Te donors in silicon

Mantas Šimėnas, 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…

cs.LG2020

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…

cs.LG2023

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…

cs.LG2023

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…

cs.LG2025

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…

cs.LG2023

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,…

cs.LG2022

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…