Author name cluster

Mingwei Lin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2026 Conference Paper

BiO-HMC: Dynamic Human-Machine Collaboration for Consensus Decision-Making via Bilevel Optimization

Yinghui Pan
Shuaijie Zhao
Shenbao Yu
Zongyang Liu
Yifeng Zeng
Han Liu
Mingwei Lin

Consensus decision-making uses crowd responses (usually from non-experts) to questions to reach a consensus answer based on human-machine collaboration. The crucial point is dynamic, which should not only enable rapid self-iteration toward the correct answer through crowd workers' responses but also adaptively suggest the next most valuable question(s) to accelerate the integration of the answer. However, existing methods reach consensus using either offline data or fixed question search structures, thereby largely sidestepping this dynamic nature. In response, we propose a bilevel optimization-based human-machine collaboration (BiO-HMC), which explores an inner & outer-level optimization to enable effective answer integration and efficient question selection. The resulting optimization problem is intractable because there is no closed-form expression in the inner-level optimization. We employ a gradient-based method and guarantee the method's theoretical convergence. Experimental results on synthetic and real-world datasets demonstrate the effectiveness and efficiency of the BiO-HMC model, i.e., achieving the highest confidence in the correct answer with the lowest labor cost.

PDF Details DOI

IROS Conference 2025 Conference Paper

MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics

Shuguang Chu
Zebin Huang
Yutong Li
Mingwei Lin
Dejun Li
Ignacio Carlucho
Yvan R. Petillot
Canjun Yang

This study introduces MarineGym, a high-performance reinforcement learning platform tailored for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of reinforcement learning compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated hydrodynamic plugin based on Isaac Sim, achieving a rollout speed of 250, 000 frames per second on a single NVIDIA RTX 3060 GPU. It also provides five models of unmanned underwater vehicles, multiple propulsion systems, and a set of predefined tasks covering core underwater control challenges. Additionally, the domain randomization toolkit allows flexible adjustments of the simulation and task parameters during training to improve the Sim2Real transfer. Further benchmark experiments demonstrate that MarineGym improves training efficiency over existing platforms and supports robust policy adaptation under various perturbations in the marine environment. We expect this platform to drive further advancements in RL research for underwater robotics. For more details about MarineGym and its applications, please visit our project page: https://marine-gym.com/.

Details

NeurIPS Conference 2024 Conference Paper

An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling

Shenbao Yu
Yinghui Pan
Yifeng Zeng
Prashant Doshi
Guoquan Liu
Kim-Leng Poh
Mingwei Lin

Student cognitive modeling (SCM) is a fundamental task in intelligent education, with applications ranging from personalized learning to educational resource allocation. By exploiting students' response logs, SCM aims to predict their exercise performance as well as estimate knowledge proficiency in a subject. Data mining approaches such as matrix factorization can obtain high accuracy in predicting student performance on exercises, but the knowledge proficiency is unknown or poorly estimated. The situation is further exacerbated if only sparse interactions exist between exercises and students (or knowledge concepts). To solve this dilemma, we root monotonicity (a fundamental psychometric theory on educational assessments) in a co-factorization framework and present an autoencoder-like nonnegative matrix co-factorization (AE-NMCF), which improves the accuracy of estimating the student's knowledge proficiency via an encoder-decoder learning pipeline. The resulting estimation problem is nonconvex with nonnegative constraints. We introduce a projected gradient method based on block coordinate descent with Lipschitz constants and guarantee the method's theoretical convergence. Experiments on several real-world data sets demonstrate the efficacy of our approach in terms of both performance prediction accuracy and knowledge estimation ability, when compared with existing student cognitive models.

PDF Details DOI

EAAI Journal 2024 Journal Article

Intelligent evaluation system for new energy vehicles based on sentiment analysis: An MG-PL-3WD method

Chao Zhang
Qifei Wen
Deyu Li
Arun Kumar Sangaiah
Mingwei Lin

As a critical strategic tool within the framework of the digital economy (DE), artificial intelligence (AI) plays a crucial role in realizing an AI-assisted economy. This novel paradigm has gained widespread acceptance from governments globally, positioning itself as a cornerstone in the practical implementation of the DE. The increasing reliance on digital means for economic transformation, the treatment of data as a critical resource, and the integration of information technologies highlight the synergy between AI and the DE. Against this backdrop, online reviews and SA play a pivotal role, offering rich data streams continually emerging on various platforms. Therefore, this article utilizes a probabilistic linguistic term set (PLTS) to establish a multi-granularity probabilistic linguistic (MG-PL) information system. This approach, through sentiment analysis (SA), enables quantitative analysis of user emotional expressions. The integration of these technological aspects holds the promise of enhancing decision-making processes, facilitating the intellectualization of economic activities, and addressing existing challenges in the application of AI within the DE domain. Initially, SA is conducted on text-based online comment data, forming a probabilistic linguistic incomplete information system. The maximum similarity method is employed to establish a probabilistic linguistic complete information system. Subsequently, an adjustable MG-PL decision-theoretic rough set (DTRS) is developed, followed by the establishment of a three-way group decision model using three-way decisions (3WD) and a directed graph. The model’s applicability, stability, and feasibility are demonstrated via a case study centered on the acquisition of new energy vehicles (NEVs).

Details DOI