Scholar
Junxiao Wang
Google Scholar ID: H6RsGygAAAAJ
KAUST, Postdoctoral Fellow
Citations & Impact
Citations
1,234
H-index
14
i10-index
16
Publications
20
Co-authors
40
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Private Training Large-scale Models with Efficient DP-SGD' accepted by NeurIPS 2025.
- Paper 'On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View' posted on arXiv in August 2025.
- Paper 'Enhancing Inductive Knowledge Graph Completion with Contextual Relation Topology Learning' accepted by Knowledge-Based Systems.
- Paper 'Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment' accepted by EMNLP 2025.
- Paper 'Federated Learning on Heterogeneous and Long-Tailed Data via Disentangled Representation' accepted by IEEE Transactions on Mobile Computing.
- Paper 'Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis' accepted by CIKM 2025 and posted on arXiv in August 2025.
- Survey paper 'A Survey on Zeroth-Order Optimization for Machine Learning' accepted by WISA 2025.
- Served as reviewer or PC member for top-tier conferences including CVPR, ICLR, AISTATS, NeurIPS, ICCV, ECCV, IJCAI, and ECAI (2024–2026).
- Invited talk at Ritsumeikan University and CCF Dalian International Seminar in 2025.
