Explanipedia

Construction of (nearly) Orthogonal Symmetric Latin Hypercube Designs Open

Kashinath Chatterjee, Christos Koukouvinos, Min‐Qian Liu · 2025

Mirror-Symmetric Orthogonal Latin Hypercubes with Attractive Space-Filling Properties Open

Chunyan Wang, Min‐Qian Liu · 2025

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding Open

Xingyu Fu, Min‐Qian Liu, Zhengyuan Yang, John Corring, Yijuan Lu , et al. · 2025

Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning sequence to arrive at the final answer. However, current mul…

Breaking the Strength-Ductility Trade-Off: Crisscross Microstructure Enhances High Entropy Alloys Fabricated Via Laser Powder Bed Fusion Open

Min‐Qian Liu, Dianyang Lin, Gang Qin, X.G. Song, Ruirun Chen , et al. · 2025

MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design Open

Jingyuan Qi, Zian Jia, Min‐Qian Liu, Wangcheng Zhan, Junkai Zhang , et al. · 2025

Strongly Coupled Designs for Computer Experiments with Both Qualitative and Quantitative Factors Open

Meng-Meng Liu, Min‐Qian Liu, Jinyu Yang · 2024

Computer experiments often involve both qualitative and quantitative factors, posing challenges for efficient experimental designs. Strongly coupled designs (SCDs) are proposed in this paper to balance flexibility in run size and stratific…

MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design Open

Jingyuan Qi, Zian Jia, Min‐Qian Liu, Wangcheng Zhan, Junkai Zhang , et al. · 2024

The discovery of novel mechanical metamaterials, whose properties are dominated by their engineered structures rather than chemical composition, is a knowledge-intensive and resource-demanding process. To accelerate the design of novel met…

Holistic Evaluation for Interleaved Text-and-Image Generation Open

Min‐Qian Liu, Zhiyang Xu, Zihao Lin, Trevor Ashby, Joy Rimchala , et al. · 2024

Interleaved text-and-image generation has been an intriguing research direction, where the models are required to generate both images and text pieces in an arbitrary order. Despite the emerging advancements in interleaved generation, the …

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks Open

Jingyuan Qi, Min‐Qian Liu, Ying Shen, Zhiyang Xu, Lifu Huang · 2024

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks,…

An Efficient Quasi-Random Sampling for Copulas Open

Sumin Wang, Chenxian Huang, Yongdao Zhou, Min‐Qian Liu · 2024

This paper examines an efficient method for quasi-random sampling of copulas in Monte Carlo computations. Traditional methods, like conditional distribution methods (CDM), have limitations when dealing with high-dimensional or implicit cop…

Towards Effective Long Conversation Generation with Dynamic Topic Tracking and Recommendation Open

Trevor Ashby, Adithya Kulkarni, Jingyuan Qi, Min‐Qian Liu, Eunah Cho , et al. · 2024

Ameli: Enhancing Multimodal Entity Linking with Fine-Grained Attributes Open

Bing Yao, Sijia Wang, Yu Chen, Qifan Wang, Min‐Qian Liu , et al. · 2024

X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects Open

Min‐Qian Liu, Ying Shen, Zhiyang Xu, Yixin Cao, Eunah Cho , et al. · 2023

Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may …

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks Open

Jingyuan Qi, Min‐Qian Liu, Ying Shen, Zhiyang Xu, Lifu Huang · 2023

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks,…

A New Class of Orthogonal Designs With Good Low Dimensional Space-Filling Properties Open

Chunyan Wang, Dennis K. J. Lin, Min‐Qian Liu · 2023

The space-filling property and orthogonality are perhaps two most desirable design properties for computer experiments.The space-filling property is appropriate for Gaussian process models, while orthogonality allows the estimated effects …

Fast Approximation of the Shapley Values Based on Order-of-Addition Experimental Designs Open

Liuqing Yang, Yongdao Zhou, Haoda Fu, Min‐Qian Liu, Wei Zheng · 2023

Shapley value is originally a concept in econometrics to fairly distribute both gains and costs to players in a coalition game. In the recent decades, its application has been extended to other areas such as marketing, engineering and mach…

Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction Open

Min‐Qian Liu, Lifu Huang · 2023

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constan…

Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization Open

Xiaochu Li, Min‐Qian Liu, Zhiyang Xu, Lifu Huang · 2023

Biomedical entity linking and event extraction are two crucial tasks to support text understanding and retrieval in the biomedical domain. These two tasks intrinsically benefit each other: entity linking disambiguates the biomedical concep…

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models Open

Jingyuan Qi, Zhiyang Xu, Ying Shen, Min‐Qian Liu, Di Jin , et al. · 2023

Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass and sequential generation process, CoT heavily relies on the…

AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes Open

Barry Menglong Yao, Yu Chen, Qifan Wang, Sijia Wang, Min‐Qian Liu , et al. · 2023

We propose attribute-aware multimodal entity linking, where the input consists of a mention described with a text paragraph and images, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where …

Sequential good lattice point sets for computer experiments Open

Xueru Zhang, Min‐Qian Liu, Dennis K. J. Lin, Yongdao Zhou · 2023

Sequential Latin hypercube designs have recently received great attention for computer experiments. Much of the work has been restricted to invariant spaces. The related systematic construction methods are inflexible while algorithmic meth…

A Construction Method for Maximin L1-Distance Latin Hypercube Designs Open

Ru Yuan, Yuhao Yin, Hongquan Xu, Min‐Qian Liu · 2023

Maximin distance designs are a kind of space-filling designs, which are widely used in computer experiments.A lot of work has been done for constructing such designs.Even so, construction of maximin distance designs with large row and colu…

Construction of Column-Orthogonal Designs with Two-Dimensional Stratifications Open

Song-Nan Liu, Min‐Qian Liu, Jinyu Yang · 2023

For the design of computer experiments, column orthogonality and space-filling are two desirable properties. In this paper, we develop methods for constructing a new class of column-orthogonal designs (ODs) with two-dimensional stratificat…

Fast Approximation of the Shapley Values Based on Order-of-Addition Experimental Designs Open

Liuqing Yang, Yongdao Zhou, Haoda Fu, Min‐Qian Liu, Wei Zheng · 2023

Shapley value is originally a concept in econometrics to fairly distribute both gains and costs to players in a coalition game. In the recent decades, its application has been extended to other areas such as marketing, engineering and mach…

A sampling scheme for estimating the prevalence of a pandemic Open

Ze Liu, Siyu Yi, Jianghu Dong, Min‐Qian Liu, Yongdao Zhou · 2023

The spread of COVID-19 makes it essential to investigate its prevalence. In such investigation research, as far as we know, the widely-used sampling methods didn’t use the information sufficiently about the numbers of the previously diagno…

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models Open

Jingyuan Qi, Zhiyang Xu, Ying Shen, Min‐Qian Liu, Di Jin , et al. · 2023

Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass and sequential generation process, CoT heavily relies on the…

Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction Open

Min‐Qian Liu, Lifu Huang · 2023

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constan…

A Method for Augmenting Supersaturated Designs with Newly Added Factors Open

Chun-Wei Zheng, Zongfeng Qi, Qiaozhen Zhang, Min‐Qian Liu · 2022

Follow-up experimental designs are popularly used in industry. In practice, some important factors may be neglected for various reasons in the first-stage experiment and they need to be added in the next stage. In this paper, we propose a …

A generic framework for coded caching and distributed computation schemes Open

Min Xu, Zixiang Xu, Gennian Ge, Min‐Qian Liu · 2022

Several network communication problems are highly related such as coded caching and distributed computation. The centralized coded caching focuses on reducing the network burden in peak times in a wireless network system and the coded dist…

Network Function Computation With Different Secure Conditions Open

Min Xu, Gennian Ge, Min‐Qian Liu · 2022

In this paper, we investigate function computation problems under different secure conditions over a network with multiple source nodes and a single sink node which desires a function of all source messages without error. A wiretapper has …

Min‐Qian Liu YOU? Author Swipe