papers

Publications (86)

cs.AI2024

FaultExplainer: Leveraging Large Language Models for Interpretable Fault Detection and Diagnosis

Abdullah Khan, Rahul Nahar, Hao Chen +2

Machine learning algorithms are increasingly being applied to fault detection and diagnosis (FDD) in chemical processes. However, existing data-driven FDD platforms often lack inte…

eess.IV2024

Deep-Learning Recognition of Scanning Transmission Electron Microscopy: Quantifying and Mitigating the Influence of Gaussian Noises

Hanlei Zhang, Jincheng Bai, Xiabo Chen +4

Scanning transmission electron microscopy (STEM) is a powerful tool to reveal the morphologies and structures of materials, thereby attracting intensive interests from the scientif…

astro-ph.IM2020

Compressive Shack-Hartmann Wavefront Sensor based on Deep Neural Networks

Peng Jia, Mingyang Ma, Dongmei Cai +3

The Shack-Hartmann wavefront sensor is widely used to measure aberrations induced by atmospheric turbulence in adaptive optics systems. However if there exists strong atmospheric t…

cond-mat.mes-hall2022

Topological Defects Induced High-Spin Quartet State in Truxene-Based Molecular Graphenoids

Can Li, Yu Liu, Yufeng Liu +9

Topological defects in graphene materials introduce exotic properties which are absent in their defect-free counterparts with both fundamental importance and technological implicat…

cs.AI2025

TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models

Haechang Kim, Hao Chen, Can Li +1

Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap betwe…

cond-mat.mes-hall2024

Ultra-Long Homochiral Graphene Nanoribbons Grown Within h-BN Stacks for High-Performance Electronics

Bosai Lyu, Jiajun Chen, Sen Wang +21

Van der Waals encapsulation of two-dimensional materials within hexagonal boron nitride (h-BN) stacks has proven to be a promising way to create ultrahigh-performance electronic de…

cs.ET2025

Real-time raw signal genomic analysis using fully integrated memristor hardware

Peiyi He, Shengbo Wang, Ruibin Mao +6

Advances in third-generation sequencing have enabled portable and real-time genomic sequencing, but real-time data processing remains a bottleneck, hampering on-site genomic analys…

math.OC2025

A Tutorial on Multi-time Scale Optimization Models and Algorithms

Asha Ramanujam, Can Li

Systems across different industries consist of interrelated processes and decisions in different time scales including long-time decisions and short-term decisions. To optimize suc…

cond-mat.mes-hall2020

Designer spin order in diradical nanographenes

Yuqiang Zheng, Can Li, Chengyang Xu +14

The magnetic properties of carbon materials are at present the focus of an intense research effort in physics, chemistry and materials science due to their potential applications i…

cond-mat.mes-hall2022

Quantum phase transition in magnetic nanographenes on a lead superconductor

Yu Liu, Can Li, Fu-Hua Xue +14

Quantum spins, referred to the spin operator preserved by full SU(2) symmetry in the absence of the magnetic anistropy, have been proposed to host exotic interactions with supercon…

cs.AR2024

Efficient Nonlinear Function Approximation in Analog Resistive Crossbars for Recurrent Neural Networks

Junyi Yang, Ruibin Mao, Mingrui Jiang +9

Analog In-memory Computing (IMC) has demonstrated energy-efficient and low latency implementation of convolution and fully-connected layers in deep neural networks (DNN) by using p…

eess.IV2023

UniMOS: A Universal Framework For Multi-Organ Segmentation Over Label-Constrained Datasets

Can Li, Sheng Shao, Junyi Qu +2

Machine learning models for medical images can help physicians diagnose and manage diseases. However, due to the fact that medical image annotation requires a great deal of manpowe…

cs.AI2026

Non-Parametric Structural Priors for Geometry Theorem Prediction

Junbo Zhao, Ting Zhang, Can Li +3

Multi-step theorem prediction is a central challenge in geometry problem solving. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit li…

cs.LG2024

FERI: A Multitask-based Fairness Achieving Algorithm with Applications to Fair Organ Transplantation

Can Li, Dejian Lai, Xiaoqian Jiang +1

Liver transplantation often faces fairness challenges across subgroups defined by sensitive attributes such as age group, gender, and race/ethnicity. Machine learning models for ou…

math.OC2026

Self-Supervised Learning of Parametric Approximation for Security-Constrained DC-OPF

Anderson Anrrango, André Quisaguano, Gonzalo E. Constante-Flores +1

This paper introduces a self-supervised learning framework for approximating the Security-Constrained DC Optimal Power Flow (SC-DCOPF) problem using a parametric linear model. The…

cs.ET2019

Harnessing Intrinsic Noise in Memristor Hopfield Neural Networks for Combinatorial Optimization

Fuxi Cai, Suhas Kumar, Thomas Van Vaerenbergh +8

We describe a hybrid analog-digital computing approach to solve important combinatorial optimization problems that leverages memristors (two-terminal nonvolatile memories). While p…

math.OC2024

PAMSO: Parametric Autotuning Multi-time Scale Optimization Algorithm

Asha Ramanujam, Can Li

Optimization models with decision variables in multiple time scales are widely used across various fields such as integrated planning and scheduling. To address scalability challen…

cs.SD2023

A Voice Disease Detection Method Based on MFCCs and Shallow CNN

Xiaoping Xie, Hao Cai, Can Li +1

The incidence rate of voice diseases is increasing year by year. The use of software for remote diagnosis is a technical development trend and has important practical value. Among…

cond-mat.mes-hall2026

Strongly entangled Quantum Spin Rings driven by Hückel rule

Manish Kumar, Deng-Yuan Li, Zhangyu Yuan +11

Quantum spin rings represent an intriguing platform for studying unconventional magnetic order and exotic quantum phases, and they are also promising materials for emerging quantum…

cs.ET2018

Long short-term memory networks in memristor crossbars

Can Li, Zhongrui Wang, Mingyi Rao +14

Recent breakthroughs in recurrent deep neural networks with long short-term memory (LSTM) units has led to major advances in artificial intelligence. State-of-the-art LSTM models w…

cs.LG2022

Unsupervised Knowledge Adaptation for Passenger Demand Forecasting

Can Li, Lei Bai, Wei Liu +2

Considering the multimodal nature of transport systems and potential cross-modal correlations, there is a growing trend of enhancing demand forecasting accuracy by learning from mu…

cs.LG2022

A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications

Can Li, Lei Bai, Lina Yao +2

Transportation is the backbone of the economy and urban development. Improving the efficiency, sustainability, resilience, and intelligence of transportation systems is critical an…

math.NA2013

Second order WSGD operators II: A new family of difference schemes for space fractional advection diffusion equation

Can Li, Weihua Deng

The second order weighted and shifted Grünwald difference (WSGD) operators are developed in [Tian et al., arXiv:1201.5949] to solve space fractional partial differential equations…

cs.CV2026

Gaussian Sequences with Multi-Scale Dynamics for 4D Reconstruction from Monocular Casual Videos

Can Li, Jie Gu, Jingmin Chen +2

Understanding dynamic scenes from casual videos is critical for scalable robot learning, yet four-dimensional (4D) reconstruction under strictly monocular settings remains highly i…

cs.CL2025

Discerning minds or generic tutors? Evaluating instructional guidance capabilities in Socratic LLMs

Ying Liu, Can Li, Ting Zhang +4

The conversational capabilities of large language models hold significant promise for enabling scalable and interactive tutoring. While prior research has primarily examined their…

math.OC2023

A Feasible Conjugate Gradient Method for Calculating -Eigenpairs of Symmetric Tensors

Jiefeng Xu, Can Li, Dong-Hui Li

In this paper, we propose a feasible conjugate gradient (FCG) method for calculating -eigenpairs of a symmetric tensor . The method is an extension of t…

physics.app-ph2025

Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing

Zhu Wang, Song Wang, Zhiyuan Du +5

The demand for edge artificial intelligence to process event-based, complex data calls for hardware beyond conventional digital, von-Neumann architectures. Neuromorphic computing,…

math.CA2015

Well-posedness and numerical algorithm for the tempered fractional ordinary differential equations

Can Li, Weihua Deng, Lijing Zhao

Trapped dynamics widely appears in nature, e.g., the motion of particles in viscous cytoplasm. The famous continuous time random walk (CTRW) model with power law waiting time distr…

cs.CV2023

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features

Song Wang, Zhu Wang, Can Li +2

In comparison to conventional RGB cameras, the superior temporal resolution of event cameras allows them to capture rich information between frames, making them prime candidates fo…

cs.HC2025

OptiChat: Bridging Optimization Models and Practitioners with Large Language Models

Hao Chen, Gonzalo Esteban Constante-Flores, Krishna Sri Ipsit Mantri +3

Optimization models have been applied to solve a wide variety of decision-making problems. These models are usually developed by optimization experts but are used by practitioners…

physics.app-ph2017

The effect of hydroxyl on dye-sensitized solar cells assembled with TiO2 nanorods

Lijian Meng, Tao Yang, Sining Yun +1

TiO2 nanorods have been prepared on ITO substrates by dc reactive magnetron sputtering technique. The hydroxyl groups have been introduced on the nanorods surface. The structure an…

cs.AI2026

Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing

Can Li, Ting Zhang, Junbo Zhao +1

Geometry Problem Solving have increasingly adopt the neuro-symbolic paradigm, combining neural intuition with symbolic rigor. However, current frameworks suffer from severe bottlen…

quant-ph2025

Enhanced charging power in nonreciprocal quantum battery by reservoir engineering

Qi-Yin Lin, Guang-Zheng Ye, Can Li +2

We propose a scheme to achieve a nonreciprocal quantum battery (QB) in the non-Hermitian (NH) system, which can overcome the intrinsic dissipation and reverse flow constraints. The…

cs.LG2020

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Lei Bai, Lina Yao, Can Li +2

Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an…

cond-mat.mes-hall2024

Real-space study of zero-field correlation in tetralayer rhombohedral graphene

Yufeng Liu, Zonglin Li, Shudan Jiang +19

Rhombohedral graphene (RG) has emerged as a promising platform for exploring exotic quantum phenomena, such as quantum magnetism, unconventional superconductivity, and fractional q…

cs.AI2026

VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs

Can Li, Ying Liu, Ting Zhang +2

Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reasoning, and domain-specific tasks. H…

cs.ET2024

FeReX: A Reconfigurable Design of Multi-bit Ferroelectric Compute-in-Memory for Nearest Neighbor Search

Zhicheng Xu, Che-Kai Liu, Chao Li +7

Rapid advancements in artificial intelligence have given rise to transformative models, profoundly impacting our lives. These models demand massive volumes of data to operate effec…

cond-mat.mes-hall2022

Catalytic growth of ultralong graphene nanoribbons on insulating substrates

Bosai Lyu, Jiajun Chen, Shuo Lou +22

Graphene nanoribbons (GNRs) with widths of a few nanometres are promising candidates for future nano-electronic applications due to their structurally tunable bandgaps, ultrahigh c…

math.OC2026

A Quadratically-Constrained Convex Approximation for the AC Optimal Power Flow

Gonzalo E. Constante-Flores, Can Li

We introduce a quadratically-constrained approximation (QCAC) of the AC optimal power flow (AC-OPF) problem. Unlike existing approximations like the DC-OPF, our model does not rely…

eess.SP2023

Realizing In-Memory Baseband Processing for Ultra-Fast and Energy-Efficient 6G

Qunsong Zeng, Jiawei Liu, Mingrui Jiang +7

To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-ef…

cs.CL2026

ERNIE 5.0 Technical Report

Haifeng Wang, Hua Wu, Tian Wu +432

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…

cs.CV2022

DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding

Liang Qiao, Hui Jiang, Ying Chen +9

This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms…

cond-mat.mtrl-sci2026

Quantum Spin-1/2 Rings Built from [2]Triangulene Molecular Units

Can Li, Manish Kumar, Ying Wang +14

Quantum spin rings represent fundamental model systems that exhibit distinctive quantum phenomena-such as quantum critical behavior and quasiparticle excitations-arising from their…

cs.AI2020

Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network

Can Li, Lei Bai, Wei Liu +2

Accurate demand forecasting of different public transport modes(e.g., buses and light rails) is essential for public service operation.However, the development level of various mod…

cs.AI2026

OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery

Qi Liu, Ruochen Hao, Can Li +1

Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms. Current LLM-based evolutionary methods often rely on…

cs.LG2024

A Transformer-Based Deep Learning Approach for Fairly Predicting Post-Liver Transplant Risk Factors

Can Li, Xiaoqian Jiang, Kai Zhang

Liver transplantation is a life-saving procedure for patients with end-stage liver disease. There are two main challenges in liver transplant: finding the best matching patient for…

math.AP2015

On the stability of exact ABCs for the reaction-subdiffusion equation on unbounded domain

Can Li

In this note we propose the exact artificial boundary conditions formula to the fractional reaction-subdiffusion equation on an unbounded domain. With the application of Laplace tr…

cs.LG2026

DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

Shraman Pal, Can Li

Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these proble…

cs.CV2021

VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations

Peng Zhang, Can Li, Liang Qiao +4

Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to th…

cs.LG2025

Trustworthy Tree-based Machine Learning by Flash-based Analog CAM with Inherent Soft Boundaries

Bo Wen, Guoyun Gao, Zhicheng Xu +5

The rapid advancement of artificial intelligence has raised concerns regarding its trustworthiness, especially in terms of interpretability and robustness. Tree-based models like R…

physics.ao-ph2020

Abrupt declines in tropospheric nitrogen dioxide over China after the outbreak of COVID-19

Fei Liu, Aaron Page, Sarah A. Strode +12

China's policy interventions to reduce the spread of the coronavirus disease 2019 have environmental and economic impacts. Tropospheric nitrogen dioxide indicates economic activiti…

cond-mat.mes-hall2024

Fabrication of Spin-1/2 Heisenberg Antiferromagnetic Chains via Combined On-surface Synthesis and Reduction for Spinon Detection

Xuelei Su, Zhihao Ding, Ye Hong +5

Spin-1/2 Heisenberg antiferromagnetic chains are excellent one-dimensional platforms for exploring quantum magnetic states and quasiparticle fractionalization. Understanding its qu…

cs.LG2024

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…

physics.ins-det2023

High-precision and low-latency widefield diamond quantum sensing with neuromorphic vision sensors

Zhiyuan Du, Madhav Gupta, Feng Xu +9

During the past decade, interest has grown significantly in developing ultrasensitive widefield diamond magnetometry for various applications. Despite attempts to improve the adopt…

cs.ET2022

Experimentally realized memristive memory augmented neural network

Ruibin Mao, Bo Wen, Yahui Zhao +8

Lifelong on-device learning is a key challenge for machine intelligence, and this requires learning from few, often single, samples. Memory augmented neural network has been propos…

math.NA2017

Local discontinuous Galerkin methods for the time tempered fractional diffusion equation

Xiaorui Sun, Fengfqun Zhao, Can Li

In this article, we consider discrete schemes for a fractional diffusion equation involving a tempered fractional derivative in time. We present a semi-discrete scheme by using the…

cond-mat.mes-hall2025

Imaging moiré flat bands and Wigner molecular crystals in twisted bilayer MoTe2

Yufeng Liu, Yu Gu, Ting Bao +16

Two-dimensional semiconducting moiré materials have emerged as a highly tunable platform for exploring novel quantum phenomena. Recently, tMoTe2 has attracted significant attentio…

cond-mat.mtrl-sci2014

Stacking-dependent energetics and electronic structure of ultrathin polymorphic VVI topological insulator nanofilms

Can Li, Torben Winzer, Aron Walsh +3

Topological insulators represent a paradigm shift in surface physics. The most extensively studied BiSe-type topological insulators exhibit layered structures, wherein neig…

cs.CR2026

Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage

Dongdong Zhao, Can Li, Xiang Yao +3

The paper proposes a clean‑label backdoor attack that stays dormant during training and becomes active only after specific camouflage samples are removed via machine unlearning, us…

#backdoor attacks#machine unlearning#clean-label#adversarial machine learning
eess.SY2022

Robust Multitarget Tracking in Interference Environments: A Message-Passing Approach

Xianglong Bai, Hua Lan, Zengfu Wang +3

Multitarget tracking in the interference environments suffers from the nonuniform, unknown and time-varying clutter, resulting in dramatic performance deterioration. We address thi…

math.OC2024

Solution Polishing via Path Relinking for Continuous Black-Box Optimization

Dimitri Papageorgiou, Jan Kronqvist, Asha Ramanujam +3

When faced with a limited budget of function evaluations, state-of-the-art black-box optimization (BBO) solvers struggle to obtain globally, or sometimes even locally, optimal solu…

cs.CV2026

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos

Can Li, Zhoujian Li, Ren Li +4

World models for deformable objects should recover not only geometry and appearance, but also underlying physical dynamics, interaction grounding, and material behavior. Learning s…

math.OC2024

A Convexification-based Outer-Approximation Method for Convex and Nonconvex MINLP

Zedong Peng, Kaiyu Cao, Kevin C. Furman +3

The advancement of domain reduction techniques has significantly enhanced the performance of solvers in mathematical programming. This paper delves into the impact of integrating c…

cs.LG2023

Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine

Pulakesh Upadhyaya, Kai Zhang, Can Li +2

Causal structure learning refers to a process of identifying causal structures from observational data, and it can have multiple applications in biomedicine and health care. This p…

cs.HC2023

Diagnosing Infeasible Optimization Problems Using Large Language Models

Hao Chen, Gonzalo E. Constante-Flores, Can Li

Decision-making problems can be represented as mathematical optimization models, finding wide applications in fields such as economics, engineering and manufacturing, transportatio…

eess.SY2023

Combinatorial-restless-bandit-based Transmitter-Receiver Online Selection for Distributed MIMO Radars With Non-Stationary Channels

Yuhang Hao, Zengfu Wang, Jing Fu +3

We track moving targets with a distributed multiple-input multiple-output (MIMO) radar, for which the transmitters and receivers are appropriately paired and selected with a limite…

cond-mat.mes-hall2018

Time-resolved quantum spin transport through an Aharonov-Casher ring

Can Li, Yaojin Li, Dongxing Yu +1

After obtaining an exact analytical time-varying solution for the Aharonov-Casher conducting ring embedded in a textured static/dynamic electric field, we investigate the spin-reso…

cs.LG2026

Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks

Hao Chen, Chendi Qian, Christopher Morris +2

Exact solution of hard combinatorial optimization problems often relies on strong convex relaxations, but solving these relaxations repeatedly inside a branch-and-bound algorithm c…

cs.IR2023

DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex

Jiongkang Ni, Xiaoliang Xu, Yuxiang Wang +4

Given a vector dataset and a query vector , graph-based Approximate Nearest Neighbor Search (ANNS) aims to build a graph index and approximately return…

cs.LG2025

Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules

Gonzalo E. Constante-Flores, Hao Chen, Can Li

Deep learning models are increasingly deployed in safety-critical tasks where predictions must satisfy hard constraints, such as physical laws, fairness requirements, or safety lim…

cs.LG2025

Hardware-Adaptive and Superlinear-Capacity Memristor-based Associative Memory

Chengping He, Mingrui Jiang, Keyi Shan +6

Brain-inspired computing aims to mimic cognitive functions like associative memory, the ability to recall complete patterns from partial cues. Memristor technology offers promising…

math.OC2024

AC-Network-Informed DC Optimal Power Flow for Electricity Markets

Gonzalo E. Constante-Flores, André H. Quisaguano, Antonio J. Conejo +1

This paper presents a parametric quadratic approximation of the AC optimal power flow (AC-OPF) problem for time-sensitive and market-based applications. The parametric approximatio…

cs.LG2024

FeBiM: Efficient and Compact Bayesian Inference Engine Empowered with Ferroelectric In-Memory Computing

Chao Li, Zhicheng Xu, Bo Wen +5

In scenarios with limited training data or where explainability is crucial, conventional neural network-based machine learning models often face challenges. In contrast, Bayesian i…

cs.ET2025

Fault-Free Analog Computing with Imperfect Hardware

Zhicheng Xu, Jiawei Liu, Sitao Huang +9

The growing demand for edge computing and AI drives research into analog in-memory computing using memristors, which overcome data movement bottlenecks by computing directly within…

cs.ET2025

Current Opinions on Memristor-Accelerated Machine Learning Hardware

Mingrui Jiang, Yichun Xu, Zefan Li +1

The unprecedented advancement of artificial intelligence has placed immense demands on computing hardware, but traditional silicon-based semiconductor technologies are approaching…

cond-mat.mes-hall2018

Memristor Crossbars with 4.5 Terabits-per-Inch-Square Density and Two Nanometer Dimension

Shuang Pi, Can Li, Hao Jiang +4

Memristor is a promising building block for the next generation nonvolatile random access memory and bio-inspired computing systems. Organizing memristors into high density crossba…

cs.CV2022

TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents

Zhanzhan Cheng, Peng Zhang, Can Li +6

Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial v…

math.NA2011

A weighted finite difference method for the fractional diffusion equation based on the Riemann-Liouville derivative

Ercília Sousa, Can Li

A one dimensional fractional diffusion model with the Riemann-Liouville fractional derivative is studied. First, a second order discretization for this derivative is presented and…

cs.AI2026

GATSim: Urban Mobility Simulation with Generative Agents

Qi Liu, Can Li, Wanjing Ma

Traditional agent-based urban mobility simulations often rely on rigid rulebased systems that struggle to capture the complexity, adaptability, and behavioral diversity inherent in…

cs.LG2025

TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting

Songtao Huang, Zhen Zhao, Can Li +1

Real-world time series often have multiple frequency components that are intertwined with each other, making accurate time series forecasting challenging. Decomposing the mixed fre…

cs.LG2026

SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems

Asha Ramanujam, Adam Elyoumi, Hao Chen +5

The paper introduces SafeOR-Gym, a benchmark suite of nine operations‑research environments designed to evaluate safe reinforcement learning algorithms on realistic planning and sc…

#safe reinforcement learning#operations research#benchmark suite#constrained mdp
cs.ET2021

Tree-based machine learning performed in-memory with memristive analog CAM

Giacomo Pedretti, Catherine E. Graves, Can Li +5

Tree-based machine learning techniques, such as Decision Trees and Random Forests, are top performers in several domains as they do well with limited training datasets and offer im…

physics.comp-ph2014

High order schemes for the tempered fractional diffusion equations

Can Li, Weihua Deng

Lévy flight models whose jumps have infinite moments are mathematically used to describe the superdiffusion in complex systems. Exponentially tempering the Levy measure of Lévy f…

cs.ET2020

Analog content addressable memories with memristors

Can Li, Catherine E. Graves, Xia Sheng +4

A content-addressable-memory compares an input search word against all rows of stored words in an array in a highly parallel manner. While supplying a very powerful functionality f…

cs.LG2024

Physics-Informed Neural Networks with Hard Linear Equality Constraints

Hao Chen, Gonzalo E. Constante Flores, Can Li

Surrogate modeling is used to replace computationally expensive simulations. Neural networks have been widely applied as surrogate models that enable efficient evaluations over com…

cs.CV2025

NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment

Shuhao Han, Haotian Fan, Fangyuan Kong +112

This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoratio…