📜 Publications

You can also find my most up-to-date and complete list of publications on my Google Scholar profile

LLMs & Reasoning

• “InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning”
  📄 paper
  Chengwei Wei, Jung-jae Kim, Longyin Zhang, Shengkai Chen, Nancy F Chen
  arXiv preprint arXiv:2603.17310, 2026

• “CoinMath: Harnessing the Power of Coding Instruction for Math LLMs”
  📄 paper | 💻 code & dataset & model
  Chengwei Wei, Bin Wang, Jung-jae Kim, Guimei Liu, Nancy F Chen
  ACL 2025 - Findings

• “Confidence-Aware Sub-Structure Beam Search (CABS): Mitigating Hallucination in Structured Data Generation with Large Language Models”
  📄 paper | 🎯 demo
  Chengwei Wei, Kee Kiat Koo, Amir Tavanaei, Karim Bouyarmane
  Technical Report, 2024

• “Resilience of Large Language Models for Noisy Instructions”
  📄 paper
  Bin Wang, Chengwei Wei, Zhengyuan Liu, Geyu Lin, Nancy F. Chen
  EMNLP 2024 - Findings

• “CRAFT: Extracting and Tuning Cultural Instructions from the Wild”
  📄 paper | 💻 code
  Bin Wang, Geyu Lin, Zhengyuan Liu, Chengwei Wei, and Nancy Chen
  In Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP, 2024 (Best Paper Award)

• “Bias and fairness in chatbots: An overview”
  📄 paper
  Jintang Xue, Yun-Cheng Wang, Chengwei Wei, Xiaofeng Liu, Jonghye Woo, C-C Jay Kuo
  APSIPA Transactions on Signal and Information Processing, 2024

• “An Overview on Generative AI at Scale with Edge-Cloud Computing”
  📄 paper
  Yun-Cheng Wang, Jintang Xue, Chengwei Wei, C-C Jay Kuo
  IEEE Open Journal of the Communications Society, 2023

• “An Overview of Language Models: Recent Developments and Outlook”
  📄 paper
  Chengwei Wei, Yun-Cheng Wang, Bin Wang, and C.-C. Jay Kuo
  APSIPA Transactions on Signal and Information Processing, 2023

• “A focused study on sequence length for dialogue summarization”
  📄 paper | 💻 code
  Wang, Bin, Chen Zhang, Chengwei Wei, and Haizhou Li
  arXiv preprint arXiv:2209.11910, 2022

Fundamental NLP

• “Word embedding dimension reduction via weakly-supervised feature selection”
  📄 paper
  Jintang Xue, Yun-Cheng Wang, Chengwei Wei, C-C Jay Kuo, et al.
  APSIPA Transactions on Signal and Information Processing, 2024

• “Synwmd: Syntax-aware word mover’s distance for sentence similarity evaluation”
  📄 paper | 💻 code
  Chengwei Wei, Bin Wang, and C-C. Jay Kuo
  Pattern Recognition Letters, 2023

• “Task-specific dependency-based word embedding methods.”
  📄 paper
  Chengwei Wei, Bin Wang, and C-C. Jay Kuo
  Pattern Recognition Letters, 2022

Speech & Audio

• “Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models”
  📄 paper | 💻 code & dataset & model
  Bin Wang, Xunlong Zou, Shuo Sun, Wenyu Zhang, Yingxu He, Zhuohan Liu, Chengwei Wei, Nancy F Chen, AiTi Aw
  ASRU 2025

• “IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models”
  📄 paper | 💻 code & dataset
  Yiming Gao, Bin Wang, Chengwei Wei, Shuo Sun, AiTi Aw
  AACL 2025

• “Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems”
  📄 paper | 💻 code & dataset
  Chengwei Wei, Bin Wang, Jung-jae Kim, Nancy F Chen
  arXiv preprint arXiv:2505.15000, 2025

• “A Green Learning Approach to Spoofed Speech Detection”
  📄 paper
  Chengwei Wei, Runqi Pang, C-C Jay Kuo
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

Computer Vision

• “Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia”
  📄 paper
  Samuel Cahyawijaya, Holy Lovenia, …, Chengwei Wei, et al.
  ACL 2025

• “Efficient Human-Object-Interaction (EHOI) Detection via Interaction Label Coding and Conditional Decision”
  📄 paper
  Tsung-Shan Yang, Yun-Cheng Wang, Chengwei Wei, Suya You, C-C Jay Kuo
  Computer Vision and Image Understanding, 2024

• “GHOI: A Green Human-Object-Interaction Detector”
  📄 paper
  Tsung-Shan Yang, Yun-Cheng Wang, Chengwei Wei, C-C Jay Kuo
  IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), 2024

• “ExpressionHop: A Lightweight Human Facial Expression Classifier.”
  📄 paper
  Chengwei Wei, C-C. Jay Kuo, Rafael Luiz Testa, Ariane Machado-Lima, and Fátima LS Nunes
  IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR), 2022