Tran Nam Nhat Anh

Built an end-to-end data preprocessing pipeline that OCR-processed approximately 1M biomedical papers from Semantic Scholar, extracted multimodal content, filtered low-quality Bio/Chem text with LLM scoring, and synthesized over 2M high-quality QA pairs for VLM training.
LoRA fine-tuned Qwen-2.5-VL-32B-Instruct on synthetic biomedical data, achieving more than 1% accuracy gains on Human Last Exam (Bio/Chem).
Performed benchmarking of Qwen-VL (7B/32B/72B) and MedGemma-4B on HLE, MMLU, BioInfoBench, PubMedQA, and related tasks.
Developed a clustering system for bio-informatics plots on approximately 500k biomedical image-caption pairs using BioMedCLIP and LLM.
Designed automated task runners for AutoML System on BioML Benchmark, including biomedical imaging, drug discovery, protein engineering, and single-cell omics, achieving 80–90th percentile leaderboard performance within 24 hours and outperforming all baseline agents.
Fine-tuned Qwen-3-8B-Instruct as a Reward Model using approximately 50k OpenReview papers to automate research idea evaluation and improve AutoML system performance.

Built data preprocessing pipeline for biomedical papers, Fine-tuned models Qwen-2.5-VL-32B-Instruct, Qwen-3-8B-Instruct, Developed clustering system for Bio-informatics plots, Designed automated task runners for AutoML System, Automated research idea evaluation with Qwen-3-8B-Instruct

Developed a modular DataLoader library to automate the downloading, parsing, and preprocessing of major recommendation datasets, streamlining the research pipeline.
Enhanced NAML by 2.3% AUC and 3.1% nDCG@10 using custom abstract embeddings.
Boosted NRMS by 0.4% nDCG@10 via concatenated multi-field context.
Investigated positional encoding for LRU4Rec, achieving 6.7% gains in Recall@1, MRR@1, and nDCG@1.
Enriched ml-100k using hierarchical LLM prompts to generate titles, entities, and abstracts.
Used VLM to extract visual keywords and descriptions from movie posters.
Trained SASRec on fused embeddings, achieving 2.0% nDCG@10 over baseline with entity-enhanced features.

• Developed a modular DataLoader library to automate the downloading, parsing, and preprocessing of major recommendation datasets, streamlining the research pipeline.• Enhanced two sequential recommendation baseline: (i) improve NAML by +2.3% AUC and +3.1% nDCG@10 using custom abstract embeddings, and (ii) boosted NRMS by +0.4% nDCG@10 via concatenated multi-field context.• Investigated positional encoding for LRU4Rec, achieving +6.7% gains in Recall@1, MRR@1, and nDCG@1.• Enriched ml-100k using (i) hierarchical LLM prompts to generate titles, entities, and abstracts, and (ii) VLM to extract visual keywords/descriptions from movie posters; trained SASRec on fused embeddings, achieving +2.0% nDCG@10 over baseline with entity-enhanced features.

Benchmarked 7B LLMs on Vietnamese tasks, including Math, Chain-of-Thought, and MCQ tasks.
Implemented GraphRAG with Neo4j for local recommendation.
Designed an OCR data pipeline featuring Kafka producers and consumers for reliable document streaming.
Integrated the pipeline with Spark and Hadoop for scalable batch processing.

• Benchmarked 7B LLMs on Vietnamese task, including Math, Chain-of-Thought, and MCQ tasks; implemented GraphRAG with Neo4j for local recommendation.• Designed an OCR data pipeline featuring Kafka producers and consumers for reliable document streaming, integrated with Spark and Hadoop for scalable batch processing.