Update data/documents/online_profiles.md

data/documents/online_profiles.md

@@ -0,0 +1,103 @@
+# Online Profiles — Nguyen Hoang Minh (Minh Hoàng Nguyễn)
+
+Curated public profile knowledge for ProfillyBot RAG.
+Sources: Google Scholar, GitHub, Hugging Face, ORCID, ResearchGate, LinkedIn.
+
+## Identity
+
+- **Full name:** Nguyen Hoang Minh / Minh Hoàng Nguyễn
+- **Also known as:** MinhDS, MinhNguyenDS
+- **Title:** Middle AI Engineer
+- **Location:** Ho Chi Minh City, Vietnam
+- **Affiliation:** University of Science - VNUHCM (Master of Science / studying Artificial Intelligence)
+- **Previous education:** Data Science at University of Information Technology (UIT)
+
+## Public profile links
+
+- Google Scholar: https://scholar.google.com/citations?user=GeZg_VwAAAAJ&hl=en
+- GitHub: https://github.com/MinhNguyenDS
+- Hugging Face: https://huggingface.co/MinhDS
+- ORCID: https://orcid.org/0009-0004-1384-3856
+- ResearchGate: https://www.researchgate.net/profile/Minh-Nguyen-914
+- LinkedIn: https://www.linkedin.com/in/nhm-li-me/
+- Portfolio website: https://sunminh-portfolio.vercel.app/
+- Behance: https://behance.net/minhhong66
+
+## Research interests / specialty
+
+Recommendation Systems, Large Language Models (LLMs), Natural Language Processing,
+Information Retrieval, Big Data, Deep Learning, and Machine Learning.
+
+## Google Scholar / publications (selected)
+
+Public Scholar profile (user GeZg_VwAAAAJ). Selected works:
+
+1. **From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring**
+   - arXiv: 2603.06424 (published Mar 2026)
+   - Authors include Minh Hoang Nguyen* et al.
+   - Venue: Journal of Science Education and Technology (Q1), peer review
+   - Topics: LLM AES, LoRA instruction tuning, RAG, DPO preference optimization, IELTS rubrics
+
+2. **Enhancing OCR for Sino–Nom / Sino-Vietnamese Language Processing via Fine-Tuned PaddleOCRv5**
+   - arXiv: 2510.04003 (published Oct 5, 2025)
+   - ACM TALIP (Q2) related track
+   - Topics: low-resource historical OCR, Han–Nom, PP-OCRv5 fine-tuning
+
+3. **Co-NAML-LSTUR: A Combined Model with Attentive Multi-View Learning and Long- and Short-term User Representations for News Recommendation**
+   - arXiv: 2507.20210 (published Jul 27, 2025)
+   - MIWAI 2025 / LNCS (Q2)
+   - GitHub: https://github.com/MinhNguyenDS/Co-NAML-LSTUR
+   - Topics: news recommendation, NAML, LSTUR, attentive multi-view learning
+
+4. **ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark**
+   - arXiv: 2607.12946
+   - Dataset on Hugging Face: https://huggingface.co/datasets/MinhDS/ViHoRec
+   - GitHub: https://github.com/MinhNguyenDS/ViHoRec
+   - Topics: Vietnamese hotel recommendation, cold-start benchmark
+
+Scholar metrics mentioned on CV snapshot: Citations ~66 | h-index 2 | i10-index 1 (subject to change on Scholar).
+
+## GitHub (MinhNguyenDS)
+
+- Profile: AI enthusiast, LLMs enthusiast, and Big Data
+- Notable repositories:
+  - **AI-pdf-books** — AI/Data books for AI/ML/LLMOps engineers (popular public repo)
+  - **Co-NAML-LSTUR** — Official implementation of Co-NAML-LSTUR (MIWAI 2025)
+  - **LLM_AES-EnL2** — Data and scripts for LLM auto-scoring of IELTS essays
+  - **ViHoRec** — Vietnamese Hotel Recommendation Dataset
+  - **ReportVi-IR-based_chatbot_system** — IR-based chatbot system project
+  - **Frontend-Tiktok_UI_Clone_Production** — TikTok UI clone (React)
+
+## Hugging Face (MinhDS)
+
+- Profile: https://huggingface.co/MinhDS
+- Interests: AI, LLMs, Big Data
+- Spaces (examples): ProfillyBot, PaddleOCR Text Recognition Fine-Tuning Demo, Florence-2 Vision Tasks Demo, GCN VN FakeNews
+- Models (examples): MinhDS/Mistral-7b-SFT-AES, MinhDS/Mistral-7b-SFT-DPO-AES
+- Datasets: MinhDS/ViHoRec
+- Storage bucket example: MinhDS/Co-NAML-STUR_Checkpoints
+
+## ORCID
+
+- ORCID iD: https://orcid.org/0009-0004-1384-3856
+- Use this persistent identifier when citing or verifying academic identity.
+
+## ResearchGate
+
+- Profile: https://www.researchgate.net/profile/Minh-Nguyen-914
+- Research network profile aligned with publications above (RecSys + LLM / NLP work).
+
+## LinkedIn
+
+- Profile: https://www.linkedin.com/in/nhm-li-me/
+- Professional networking profile for Nguyen Hoang Minh (Middle AI Engineer).
+- Aligns with industry roles documented in the CV (e.g., AI Engineer at ZIM Academy; previously Vietnam Food).
+
+## Industry experience snapshot (from CV knowledge)
+
+- **AI Engineer — ZIM Academy** (Edtech): product ownership around ZIM Dictionary / AI Tutor / IELTS Mock Test AI; AWS, Kubernetes, Docker, Terraform; recommendation and NLP products.
+- **AI Engineer — Vietnam Food**: internal AI platform, RAG Q&A, OCR tools, Generative AI training for staff.
+
+## How to contact / verify
+
+Prefer the links listed above (Scholar, GitHub, Hugging Face, ORCID, ResearchGate, LinkedIn) for the most up-to-date publications, code, and professional activity.