Work & Project Experience

Large Language Model and Logical Reasoning (Ph.D. Main Topic) UoA, Auckland, New Zealand
Research & Development Project Leader/Developer 02/20 – 09/25
  • Recipient of research funding for the project Strong AI Lab (Grant No. 5000675), awarded by the Tertiary Education Commission under the Entrepreneurial Research Funding program, with a total grant amount of NZD 9.6 million. Qiming Bao was primarily responsible for the logical reasoning research direction within this project.
  • We have developed an iterative enhancement framework based on LLM for generating explanations. The framework iteratively interacts between an explanation generation module ad an explanation evaluation module to enhance the quality of the generated explanations. Our paper has been accepted by AAAI Proceedings (2025) and AGI@ICLR (2024). paper and source code.
  • Our method "AMR-LDA" (GPT-4 + AMR-LDA Prompt Augmentation) achieved #1 on the ReClor leaderboard. We are the first group scored above 90% on the hidden test set around the world. Our paper has been accepted by the Findings of ACL-24 and LLM@IJCAI'23 respectively. paper, source code and model weights.
  • We evaluated generative and discriminative large language models on out-of-distribution logical reasoning tasks. While these models perform well on standard benchmarks, even minor changes in the input lead to significant performance drops, highlighting their limited reasoning capabilities. Our paper was accepted at LLM@IJCAI'23 paper and IJCAI 2024 paper (cited over 100 times), and the corresponding source code is available on GitHub.
  • To address depth imbalance in multi-step reasoning datasets and enhance model performance, we created the IMA-GloVe-GA model, combining DeepLogic with Gated Attention. Additionally, we developed a larger dataset, PARARULE-Plus, for deep multi-step reasoning over natural language. We published the paper, code and data and presentation recording on IJCLR-NeSy-22.
  • We built up a dataset called AbductionRules to increase the Transformer's performance on the tasks requiring abduction reasoning. We published the paper, code and data on the Findings of ACL-22.
  • PARARULE Plus (Multi-step deductive reasoning) and AbductionRules (Abductive reasoning) datasets are collected and merged as part of LogiTorch.ai, ReasoningNLP, Prompt4ReasoningPapers, OpenAI/Evals, A Survey on Evaluation of Large Language Models and Reasoning Language Models: A Blueprint.
  • OpenAI Evals contributions: github.com/openai/evals#648, github.com/openai/evals#651.
  • Additional reinforcement learning projects: github.com/14H034160212/Explanation-Generation and github.com/14H034160212/lemo.
Adjunct Associate Professor Beijing International Studies University (BISU), Beijing, China
Adjunct Associate Professor 2025 – Now
  • Adjunct appointment since 2025; involved in academic collaboration and mentoring on AI/NLP/multimodal systems.
  • Research focus (BISU): Multimodal Experiments for Short Drama Translation (Subtitle Recognition + Translation + TTS). Built a multimodal subtitle translation system for short dramas, covering Subtitle Recognition (VLM/OCR), Subtitle Translation (LoRA fine-tuning), and Japanese TTS (zero-shot voice cloning), with scripted evaluation and reproducible environments. Project reference: github.com/14H034160212/translation
  • Subtitle recognition benchmarking across Qwen2-VL / Qwen3-VL / InternVL2 and traditional OCR baselines (EasyOCR, RapidOCR); ran FPS sensitivity ablation (1fps/2fps/5fps) and temporal deduplication to improve subtitle recall for fast-paced dialogue.
  • TTS comparison (GPT-SoVITS v3 / F5-TTS / EdgeTTS) using Whisper-based WER/CER; implemented Adaptive Fusion (ASR + OCR) to correct ASR hallucinations using visual context.
  • Status: Manuscript is under submission. In parallel, actively preparing proposals for the National Natural Science Foundation of China (NSFC).
Applied AI Systems & Decision Optimisation (Selected Projects) Auckland, New Zealand
Personal / Mentored Engineering Projects 2025 – Now
  • AlphaTrader — OpenClaw + DeepSeek stock prediction / signal + backtesting platform; includes Docker, GitHub Actions, unit tests, automated regression tests, and reproducible experiment pipelines. Project reference: github.com/14H034160212/AlphaTrader
  • AuroraBid — RL + Bandit ad bidding / auction demo (OAG Career mentor); includes reproducible simulation runs with CI/CD automation, tests, and experiment tracking patterns. Project reference: github.com/14H034160212/AuroraBid
Head of AI — Cognitive ChatGPT Product MVP (GenAI) Kerrio.ai (Invested by the son of Otto Happel, a German billionaire and former CEO of GEA), Auckland, New Zealand
Head of AI / Lead Engineer (Hands-on MVP Builder) 11/25 – Now
  • Owned end-to-end delivery of a cognitive ChatGPT-style AI product MVP, from use-case definition and rapid prototyping to implementation and iteration based on user feedback.
  • Built a coaching-oriented conversational AI pipeline leveraging LLM prompting and structured training data to improve response quality and user outcomes, focusing on maintainability and fast experimentation.
  • Established an evaluation and iteration loop (data collection → prompt/logic refinement → regression checks) to deliver predictable quality improvements across MVP releases.
  • Collaborated with product and stakeholders to translate requirements into technical milestones, delivering in agile sprint cycles.
  • Project reference: github.com/14H034160212/gptcoaching_mi_training
Enhancing Max Sequence Length in Large Multimodal Models Xtracta (Accredited Employer), Auckland, New Zealand
Artificial Intelligence Researcher/Engineer 07/22 – now
  • Investigated and implemented alternative attention mechanisms to extend the effective sequence length in multi-modal document processing models such as LayoutLMv3 and ERNIE-LayoutX.
  • By applied the sliding window technique and a global attention mask from Longformer to extend the maximum sequence length from 512 to 4096, which model among LayoutLMv3 and ERNIE-LayoutX achieves a higher F1 score on the XFUND, FUNSD and other company internal datasets without significantly increasing GPU memory usage.
  • Replicated the multi-task, multimodal pre-training code for LayoutLMv3, which Microsoft did not open source, including masked language modeling, masked image modeling, and word-patch alignment.
  • Integrated DeepSpeed and adapters into ERNIE-LayoutX and LayoutLMv3, which can reduce training costs, result in a smaller model size, and make it easier to deploy in the production environment.
  • Successfully applied for the Research & Development Tax Incentive (RDTI) grants from Callaghan Innovation (New Zealand's Innovation Agency) for both 2022 and 2023.
  • Integrated Flash-Attention 2 into Self-Attention can help ERNIE-LayoutX reduce maximum training GPU memory usage by up to 50% under FP16.
  • Applied affine transformations for data augmentation to train the model and improve the robustness of line alignment issues for document extraction.
  • By using the PEFT adapter, Flash-Attention 2 and GPTQ int4 quantization to continually train the Qwen3-VL-8B and make Qwen3-VL-8B training on 8*H200 GPU.
  • Adding page embeddings to vision-language models (Qwen3-VL-8B and ERNIE-LayoutX) can improve their performance on fields that frequently appear on each page of a multi-page document (more than 15%).
Abstract Extraction and Multi-Turn Dialogue System Advanced Institute of Information Technology, Peking University, Hangzhou, China
Research and Development Engineer 11/19 – 02/20
  • We developed and researched a robot-based system including automatic abstract extraction, text segmentation, theme prediction, and multi-turn question answering.
  • Investigation and standard documentation of robot-related technologies.
  • We built a well-encapsulated API to implement meeting record document processing based on the abstract extraction, text segmentation, and theme prediction.
HHH: An Online Medical Chatbot System Precision Driven Health & Orion Health, Auckland, New Zealand
Research Project Leader and Developer 11/18 – 04/19
  • We developed a medical text similarity algorithm called HBAM using Pre-trained Language Model and Knowledge Graph.
  • Compared with BERT and MaLSTM models, HBAM performs higher test accuracy than the two Deep Learning models respectively github.com/14H034160212/HHH-An-Online-Question-Answering-System-for-Medical-Questions, news, recording and published paper on ACSW-20.
  • NEW: Built a medical PII detection and redaction pipeline using spaCy, automatically identifying and replacing sensitive information for privacy-preserving training and inference; project backed by AUT Venture investment (NZD 20,000).

Education

University of Auckland (UoA)Auckland, New Zealand
Ph.D. of Computer Science supervised by Prof. Michael Witbrock and Assoc Prof. Jiamou Liu 02/20 – 09/25
University of Auckland (UoA)Auckland, New Zealand
Bachelor of Science (Honours) in Computer Science (First Class), GPA: 7/9 07/18 – 09/19
  • Precision Driven Health & Orion Health Summer Research Scholarship

Paper List

  • Qiming Bao, Juho Leinonen, Alex Yuxuan Peng, Wanjun Zhong, Tim Pistotti, Alice Huang, Paul Denny, Michael Witbrock, Jiamou Liu. Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models, Proceedings of the AAAI Conference on Artificial Intelligence (2025). https://ojs.aaai.org/index.php/AAAI/article/view/35164
  • Qiming Bao, Alex Peng, Zhenyun Deng, Wanjun Zhong, Gaël Gendron, Neşet Tan, Nathan Young, Yang Chen, Yonghua Zhu, Michael Witbrock, Jiamou Liu. Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning., The Findings of ACL (2024). https://doi.org/10.18653/v1/2024.findings-acl.353
  • Qiming Bao, Gaël Gendron, Alex Peng, Neset Tan, Michael Witbrock, Jiamou Liu. Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning., ICONIP (2024). https://doi.org/10.48550/arXiv.2310.09430
  • Qiming Bao, Alex Peng, Tim Hartill, Neset Tan, Zhenyun Deng, Michael Witbrock, Jiamou Liu. Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation, IJCLR-NeSy (2022). https://ceur-ws.org/Vol-3212/paper15.pdf
  • Nathan Young, Qiming Bao, Joshua Ljudo Bensemann, Michael J. Witbrock. AbductionRules: Training Transformers to Explain Unexpected Inputs, The Findings of ACL (2022). https://doi.org/10.18653/v1/2022.findings-acl.19
  • Gaël Gendron, Qiming Bao, Michael Witbrock, Gillian Dobbie. Large Language Models Are Not Strong Abstract Reasoners, IJCAI (2024). https://www.ijcai.org/proceedings/2024/693
  • Lin Ni, Qiming Bao, Xiaoxuan Li, Qianqian Qi, Paul Denny, Jim Warren, Michael Witbrock, Jiamou Liu. DeepQR: Neural-based Quality Ratings for Learnersourced Multiple-Choice Questions, Proceedings of the AAAI Conference on Artificial Intelligence (2022). https://doi.org/10.1609/aaai.v36i11.21562
  • Qianqian Qi, Qiming Bao*, Alex Yuxuan Peng, Jiamou Liu, Michael Witbrock. A Dynamic Prompt-tuning Method for Data Augmentation with Associated Knowledge, ICLR TinyPapers (2023). https://openreview.net/pdf?id=hli7A0ioiS_
  • Qiming Bao, Lin Ni, Jiamou Liu. HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention, ACSW (2020). https://doi.org/10.1145/3373017.3373049
  • Zhongsheng Wang, Jiamou Liu, Qiming Bao, Hongfei Rong, Jingfeng Zhang. ChatLogic: Integrating Logic Programming with Large Language Models for Multi-step Reasoning, NucLeaR@AAAI (2024). https://doi.org/10.48550/arXiv.2407.10162
  • Neset TAN, Trung Nguyen, Josh Bensemann, Alex Peng, Qiming Bao, Yang Chen, Mark Gahegan, Michael Witbrock. Multi2Claim: Generating Scientific Claims from Multi-Choice Questions for Scientific Fact-Checking, EACL (2023). https://doi.org/10.18653/v1/2023.eacl-main.194
  • Neset TAN, Alex Peng, Joshua Bensemann, Qiming Bao, Tim Hartill, Mark Gahegan, Michael Witbrock. Input-length-shortening and text generation via attention values, AAAI-EMC^2 (2023). https://doi.org/10.48550/arXiv.2303.07585

    • Invited Speaker/Visiting Scholar

  • Microsoft Research Asia Invited Talk 2022 invited by Dr. Bei Chen (Invitation Letter) (Presentation Slide) (Recording)
  • Samsung AI Center Cambridge UK Invited Talk 2022 invited by Dr. Cristina Cornelio(Invitation Letter) (Presentation Slide) (Recording)
  • IEEE Vehicular Technology Society (VTS) New Zealand North Chapter and IEEE New Zealand North Section SIGHT Group 2022 invited by Dr. William Liu (Invitation Letter) (Presentation Slide) (Recording)
  • ZJU-NLP Group, Zhejiang University 2023 invited by Prof. Huajun Chen and Prof. Ningyu Zhang
  • NLP Group, The University of Melbourne Invited Talk 2023 invited by Mr. Ming-Bin Chen and Dr. Jey Han Lau (Invitation Letter) (Presentation Slide)
  • Institute of Automation, Chinese Academy of Sciences Invited Talk 2023 (Invitation Letter) (Presentation Slide)
  • University of Massachusetts - Amherst Invited Talk 2024 invited by Prof. Andrew Lan (Invitation Letter) (Presentation Slide)
  • Penn State University & University of Auckland Online Workshop 2024 Day 1 Session 2 Children's Future, Intercultural Learning (Invitation Letter) (Presentation Slide) (Recording)
  • Logic and AI Seminar 2025 (Tsinghua University & Peking University) invited by Prof. Fenrong Liu and A/Prof. Haoxuan Li (Invitation Letter)
  • Max Planck Institute For Software Systems invited by Prof. Adish Singla (Invitation Letter) (Presentation Slide)
  • Technical University of Munich invited by Dr. Stefan Fuchs and Prof. Dr.-Ing. André Borrmann (Invitation Letter)