AI Research Scientist / Research Engineer
AI Research Scientist and Research Engineer specializing in LLMs, long-context VLMs, logical reasoning, multimodal document AI, and intelligent document processing. PhD in Computer Science, University of Auckland.
AI Researcher and Engineer @ Xtracta
LLMs + Long-Context VLMs + Logical Reasoning + Intelligent Document Processing
Ex-AIIT, Peking University, MSRA, Samsung AI UK
PhD, Strong AI Lab & NAOInstitute, University of Auckland
Qiming Bao is an AI Research Scientist and Engineer at Xtracta in Auckland, New Zealand, working on multimodal document AI, intelligent document processing, and production-oriented vision-language model adaptation. His current work includes continual training and evaluation of models such as Qwen3.5, Gemma, InternVL, and Qwen-VL with PEFT/LoRA adapters, FlashAttention 2, and GPTQ int4 quantization, as well as long-context optimization for document understanding models such as LayoutLMv3 and ERNIE-LayoutX through efficient attention mechanisms, global attention masks, multimodal pre-training replication, and deployment-focused system improvements.
Qiming Bao received his PhD in Computer Science from the Strong AI Lab and NAOInstitute at the University of Auckland, supervised by Professor Michael Witbrock and Associate Professor Jiamou Liu. His research focuses on large language models, post-training and alignment, logical reasoning, neural-symbolic AI, multimodal document AI, and world-model-inspired cognitive architectures. His recent work includes Hybrid-DPO for balancing logical grounding and fluency in LLMs, Conflict-Aware Fusion for mitigating logic inertia under contradictory evidence, and AMR-based logic-driven data augmentation for robust deductive reasoning. Before joining Xtracta, he worked at AIIT at Peking University on automatic abstract generation and GPT-2 based dialogue systems, and also contributed to early medical AI research through projects with Precision Driven Health & Orion Health.
Qiming has published in leading AI and NLP venues including ACL, AAAI, IJCAI, EACL, and IJCLR-NeSy. His AMR-LDA method achieved the #1 ranking on the ReClor leaderboard, becoming one of the first systems to exceed 90% accuracy on the hidden test set, and his datasets, including PARARULE-Plus and AbductionRules, have been adopted by multiple reasoning benchmark projects. Since 2025, he has served as an Adjunct Associate Professor and collaboration supervisor at Beijing International Studies University (BISU), where he works on geospatial disaster-response AI agents, remote-sensing foundation models, and multimodal translation systems. He is also an AI Technical Lead and advisor for Kerrio.ai, building LLM-based dialogue training and evaluation systems, and develops agentic AI projects involving financial trading agents, reinforcement-learning auction simulators, and privacy-preserving accounting automation. He has delivered invited talks or academic visits at institutions including Microsoft Research Asia, Samsung AI Center Cambridge UK, Zhejiang University, the University of Melbourne, the Chinese Academy of Sciences, the University of Massachusetts Amherst, Penn State University, Tsinghua University, Max Planck Institute for Software Systems, and the Technical University of Munich.
Large Language Models (LLMs), Vision-Language Models (VLMs), Long-Context Modeling, Logical Reasoning, Neural-Symbolic AI, Multimodal Document AI, Intelligent Document Processing, Document Understanding, OCR, and Information Extraction.
