We stand with Ukraine

We stand with Ukraine

Wei Zhang

Orcid: 0000-0002-1533-6979

Affiliations:

National University of Singapore, Department of Mechanical Engineering, Singapore

According to our database¹, Wei Zhang authored at least 39 papers between 2017 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Links

Online presence:

on orcid.org

On csauthors.net:

Bibliography

2026

MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models.

[DOI]

,

,

,

,

,

,

,

,

,

,

,

CoRR, April, 2026

Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration.

[DOI]

,

,

,

,

,

,

CoRR, March, 2026

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models.

[DOI]

,

,

,

,

,

,

CoRR, March, 2026

ERL-Fill: An Emotion-Aware Reinforcement Learning Framework With Staged Pretraining for Gas-Solid Flow Filling Control.

[DOI]

,

,

,

IEEE Trans. Ind. Electron., February, 2026

Rethinking the Role of LLMs in Time Series Forecasting.

[DOI]

,

,

,

,

,

CoRR, February, 2026

SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models.

[DOI]

,

,

,

,

,

,

,

,

,

,

CoRR, January, 2026

Curriculum-Enhanced Reinforcement Learning for Robust Humanoid Locomotion.

[DOI]

,

,

,

,

IEEE Trans Autom. Sci. Eng., 2026

Understanding domain-specific attribute constraints in multimodal sentiment analysis via ensemble multimodal large language models with structured multistage prompts.

[DOI]

,

,

,

,

,

Expert Syst. Appl., 2026

A novel two-stage intelligent Kalman filter for maneuvering target tracking.

[DOI]

,

,

,

,

,

Eng. Appl. Artif. Intell., 2026

MCellPSO-PD: A multi-subgroup cellular PSO method for packing density measurement in gas-solid-phase flow.

[DOI]

,

,

,

,

,

Appl. Soft Comput., 2026

2025

LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model.

[DOI]

,

,

,

,

,

,

,

CoRR, August, 2025

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning.

[DOI]

,

,

,

,

,

,

,

,

,

CoRR, May, 2025

MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos.

[DOI]

,

,

,

,

CoRR, May, 2025

DRL-DCLP: A Deep Reinforcement Learning-Based Dimension-Configurable Local Planner for Robot Navigation.

[DOI]

,

,

,

,

,

IEEE Robotics Autom. Lett., April, 2025

Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning.

[DOI]

,

,

,

,

,

,

CoRR, March, 2025

Beyond Visibility Limits: A DRL-Based Navigation Strategy for Unexpected Obstacles.

[DOI]

,

,

,

,

,

,

CoRR, March, 2025

Achieving Stable High-Speed Locomotion for Humanoid Robots with Deep Reinforcement Learning.

[DOI]

,

,

,

,

,

Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2025

Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation.

[DOI]

,

,

,

,

,

,

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025

MAER-Nav: Bidirectional Motion Learning Through Mirror-Augmented Experience Replay for Robot Navigation.

[DOI]

,

,

,

,

,

,

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025

Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models.

[DOI]

,

,

,

,

,

,

,

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Context Guided Transformer Entropy Modeling for Video Compression.

[DOI]

,

,

,

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks.

[DOI]

,

,

Zena Al-Khalili

,

,

,

Dietrich Klakow

,

,

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs.

[DOI]

,

,

,

,

,

,

,

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Corrected Soft Actor Critic for Continuous Control.

[DOI]

,

,

,

,

,

CoRR, 2024

DDCNN: A Promising Tool for Simulation-to-reality UAV Fault Diagnosis.

[DOI]

,

,

,

,

,

Proceedings of the IEEE International Conference on Cybernetics and Intelligent Systems, 2024

Assessing "Implicit" Retrieval Robustness of Large Language Models.

[DOI]

,

Rexhina Blloshmi

,

,

,

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models.

[DOI]

,

,

,

,

,

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

Difference-based Deep Convolutional Neural Network for Simulation-to-reality UAV Fault Diagnosis.

[DOI]

,

,

,

CoRR, 2023

Simulation-to-reality UAV Fault Diagnosis with Deep Learning.

[DOI]

,

,

,

CoRR, 2023

2021

Danger-Aware Adaptive Composition of DRL Agents for Self-Navigation.

[DOI]

,

,

Unmanned Syst., 2021

Learn to Navigate Maplessly With Varied LiDAR Configurations: A Support Point-Based Approach.

[DOI]

,

,

IEEE Robotics Autom. Lett., 2021

Enhancing the Generalization Performance and Speed Up Training for DRL-based Mapless Navigation.

[DOI]

,

,

CoRR, 2021

2020

An Evolutional Algorithm for Automatic 2D Layer Segmentation in Laser-aided Additive Manufacturing.

[DOI]

,

,

,

,

,

Jerry Y. H. Fuh

,

CoRR, 2020

Map-less Navigation: A Single DRL-based Controller for Robots with Varied Dimensions.

[DOI]

,

,

CoRR, 2020

2019

Behavior Switch for DRL-based Robot Navigation.

[DOI]

,

Proceedings of the 15th IEEE International Conference on Control and Automation, 2019

2018

ACDIN: Bridging the gap between artificial and real bearing damages for bearing fault diagnosis.

[DOI]

,

,

,

,

,

Neurocomputing, 2018

Danger-aware Weighted Advantage Composition of Deep Reinforcement Learning for Robot Navigation.

[DOI]

,

,

CoRR, 2018

Bearing Fault Diagnosis Using Fully-Connected Winner-Take-All Autoencoder.

[DOI]

,

,

,

IEEE Access, 2018

2017

A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals.

[DOI]

,

,

,

,

Sensors, 2017

Loading...