Xinbao Qiao
Q is a lens: search the world, question the model.To see farther, ask better questions.Where curiosity meets evidence, discovery begins.Let the machine learn. Keep the question human.Learn from the world, not just the dataset.A model's limits are not the world's limits.In models we question; in evidence we trust.
Latest Updates7 updates“When Sample Selection Bias Precipitates Model Collapse” accepted at ICML 2026Accepted paper at ICML 2026.
- “When Sample Selection Bias Precipitates Model Collapse” accepted at ICML 2026
Accepted paper at ICML 2026.
- Completed master’s degree
M.Eng. in Artificial Intelligence, Zhejiang University.
- “Beyond Binary Erasure: Soft-Weighted Unlearning for Fairness and Robustness” accepted at AAAI 2026
Accepted paper at AAAI 2026.
- Started full-time research internship
Six-month full-time research internship on trustworthy LLMs at NUSRI-CQ.
- Started master’s degree
M.Eng. in Artificial Intelligence, Zhejiang University.
- Completed bachelor’s degree
B.Eng. in Communication Engineering, Shandong University.
Browse Xinbaopedia
Browse view
Research topics
Core research
- ResearchOverview of Xinbao Qiao's research directions and linked topic pages.
- AI and NetworksPrimary research topic for Qiao Xinbao, covering AI systems under networked data and communication constraints.
- Data Centric MLResearch topic focused on data quality, selection, valuation, correction, and governance.
Methods and geometry
- Machine UnlearningResearch topic on removing or correcting data influence from trained models.
- Distributed Wasserstein BarycenterConcept page for Qiao's work on computing Wasserstein barycenters from distributed local measures.
- Influence FunctionsConcept page for estimating how training examples affect learned models.
Reliability and trust
- Synthetic DataResearch topic on synthetic data, recursive training, low-resource verification, selection bias, and model collapse.
- Fairness and RobustnessConcept page for fairness and robustness as data-centric correction objectives.
- LLM ReliabilityConcept page for reliability issues in large language model systems.
Publications and projects
Indexes
- PublicationsPublication list for Qiao Xinbao.
- ProjectsResearch projects and project clusters.
Selected publications
- Hessian-Free Online Certified UnlearningICLR 2025 paper on efficient Hessian-free certified machine unlearning.
- Beyond Binary Erasure: Soft-Weighted Unlearning for Fairness and RobustnessAAAI 2026 paper on soft-weighted unlearning for fairness and robustness correction.
- When Sample Selection Bias Precipitates Model CollapseICML 2026 paper on low-resource verification regimes, sample-selection bias, model collapse, and collaborative Wasserstein-geometry proxies.
- DynFrs: An Efficient Framework for Machine Unlearning in Random ForestICLR 2025 paper on efficient machine unlearning for random forests.
Project pages
- AI and NetworksPrimary research topic for Qiao Xinbao, covering AI systems under networked data and communication constraints.
- Collaborative EvaluationConcept page for evaluating models or data processes across multiple parties.
Affiliations
Profile
- Curriculum VitaeAcademic CV summary for Xinbao Qiao.
- EducationEducation timeline for Qiao Xinbao.
- ExperienceResearch experience and affiliations.
Institutions
- The Chinese University of Hong KongCurrent doctoral institution of Xinbao Qiao.
- Zhejiang UniversityMaster's institution of Xinbao Qiao.
- Shandong UniversityUndergraduate institution of Xinbao Qiao.
- NUSRI-CQResearch internship institution of Xinbao Qiao.
Academic network
- Angela Yingjun ZhangCUHK Information Engineering professor and doctoral advisor of Xinbao Qiao.
- Meng ZhangZhejiang University faculty member and master's advisor of Xinbao Qiao.