Foundations + Research
A bilingual knowledge base on mathematics, statistics, machine learning, NLP, LLMs, model evaluation, and applied AI research. The goal is simple: make the foundations reusable, then connect them to real experiments.
Foundations
This track is where existing high-quality resources become my own explanations, notes, examples, and interview-ready mental models.
Linear algebra, calculus, optimization, graphs, and representation spaces explained through ML and NLP examples.
Probability, distributions, confidence intervals, bootstrap testing, hypothesis tests, and uncertainty in evaluation.
Splits, generalization, model selection, cross-validation, losses, regularization, and practical training workflows.
Tokenization, embeddings, Transformers, fine-tuning, prompting, sequence models, and language-specific evaluation.
Experiment repositories, config-driven pipelines, logging, annotation sheets, demos, and reproducible analysis.
Research & Applications
This track avoids boxing the blog into one thesis topic. It groups research by capability: building, evaluating, explaining, retrieving, and applying AI systems.
Machine translation, multilingual NLP, low-resource adaptation, terminology, domain adaptation, and language variation.
Metrics, benchmark design, statistical testing, ablations, error analysis, human evaluation, and robustness.
Interpretability, bias analysis, attribution, model auditing, SHAP/LIME, Shapley values, and controlled evaluation.
Information retrieval, RAG, long documents, graph retrieval, evidence grounding, and document intelligence.
Data pipelines, classification, forecasting, information extraction, deployment, product demos, and applied analytics.
Posts may be in English, Chinese, or bilingual. Foundations posts often start from strong public resources; research posts connect those foundations to my own experiments.
A research story about turning 15 years of annual-report PDFs into an auditable benchmark for retrieval, GraphRAG, failure recovery, and grounded question answering.
A visual guide to RAG document preparation: PDF parsing, layout and tables, evidence objects, chunking, metadata, embeddings, and indexes.
From documents, chunks, and embeddings to retrieval, reranking, evidence completeness, augmentation, and generation: a complete visual foundation for RAG.
从 15 年企业年报 PDF 出发，构建可审计的检索 benchmark，并研究 GraphRAG、失败恢复和有证据支撑的问答。
用三张图理解 RAG 的文档准备：PDF 解析、布局与表格、evidence objects、chunking、metadata、embeddings 和索引。
从文档、Chunk 和 Embedding，到检索、重排序、证据完整性、上下文增强与生成：系统理解 Retrieval-Augmented Generation 的完整基础流程。
Portfolio pages show what I built. These notes explain the foundations, decisions, experiments, and tradeoffs behind the work.