· Xiaojing Yang · NLP and LLMs
Parameter-Efficient Fine-Tuning
Why LoRA and adapters are useful when full fine-tuning is too expensive or unstable.
Blog
Foundations and research notes on mathematics, statistics, machine learning, NLP, LLMs, model evaluation, and applied AI systems.
- · Xiaojing Yang · Statistics
PCA: From Variance to Representation
PCA explains how variance, projection, and representation are connected.
- · Xiaojing Yang · Machine Learning
Pipelines and Data Leakage
Why preprocessing belongs inside the validation pipeline, not before the split.
- · Xiaojing Yang · Statistics
Power Analysis: How Many Experiments Do You Need?
Power analysis connects sample size, effect size, and the chance of detecting a real improvement.
- · Xiaojing Yang · Statistics
Probability Distributions for Machine Learning
How distributions become assumptions about data, labels, errors, and model behavior.
- · Xiaojing Yang · NLP and LLMs
Prompting and Instruction Following
Prompting as task specification, interface design, and evaluation risk.