Code Is Cheap, Show Me The Idea
AI made the first demo cheaper. The scarce thing now is the idea the model would not have found on its own.
The AI-Era Newspaper Is A Feed You Have To Interpret
I never became a newspaper person, but AI gave me a stranger version of the habit: reading releases, benchmarks, replies, and changelogs until the field starts to become legible.
Personalized AI Agents And The Visual Novel Design Stack
Personalized agents do not just need a warmer prompt. They need earned continuity: memory, callbacks, pacing, and boundaries the user can see.
Vibe Researching Is Not Outsourcing Your Thinking
Claude made parts of a multi-agent RL project faster, but the hard part stayed mine: deciding where agents synchronize and what claims were earned.
Writing Technical Blogs After AI
AI can generate explanations on demand. The posts I still want to publish need to carry judgment, contact with reality, and a way of thinking.
Heron Event-Driven MARL
A domain-agnostic MARL framework for evaluating trained policies under heterogeneous event-driven execution and realistic observability constraints
ResumeAssist
A private, configurable AI resume assistant with LangChain agents, CV rendering, and a full-stack review workflow
LLM Validator
A configurable LLM benchmarking template for repeatable model, prompt, dataset, and metric validation
Model Iteration Series: Validating Model Infra
Infrastructure checks for LLM model changes before QA: compatibility, latency, and cost.
Model Iteration Series: Validating Model Research
How to validate LLM model-change proposals before they move into infra, QA, and product testing.
Deployable AI
A lightweight local inference-serving toolkit for registering models and exposing prediction endpoints quickly
Model Iteration Series: Intro
A practical overview of how LLM model changes move from research validation to staging and production.
Testing in Machine Learning
A practical checklist for testing data, models, ML systems, and CI/CD pipelines.
Prompt Engineering Whitebook
A practical handbook for designing, testing, and debugging prompts for LLM applications.
A Good Python Project Template to Use as a Starting Point
A practical Python project scaffold for packaging, testing, linting, documentation, and CI.
Writing Quality Code for Machine Learning
Practical notes on turning ML code from proof-of-concept scripts into maintainable systems.
MLOps Post-Training Considerations
A practical overview of experiment tracking, model registries, serving, and monitoring after model training.
Understanding Distributed Training in Deep Learning
A practical map of data parallelism, model sharding, pipeline parallelism, launch tools, and the bottlenecks that usually decide whether distributed training is worth it.
Some Tricks in Real-World Machine Learning Engineering
Practical notes on moving from notebooks to pipelines, handling missing values, scaling features, encoding categories, and keeping ML code production-friendly.
Quantization in Deep Learning
A practical guide to post-training quantization, quantization-aware training, mixed precision, and low-bit model deployment.
Deep Learning Training: A Practical Guide
A practical guide to optimizer choice, learning-rate schedules, stability, memory pressure, throughput, checkpointing, and experiment management during deep learning training.
Fine-Tuning in LLMs
A practical overview of supervised fine-tuning, LoRA, prompt tuning, adapters, RLHF, DPO, data quality, and evaluation for large language models.
Starting Your AI/ML Project: From Research to Engineering
A practical checklist for turning an AI or ML idea into an engineering project with clear goals, data contracts, evaluation, infrastructure, and operational risk management.
Testing Machine Learning Systems
A compact guide to unit tests, data tests, model behavior tests, evaluation, regression tests, and production checks for machine learning systems.
Deep Learning System Design: A Checklist, Part II
A practical checklist for the production side of deep learning systems: packaging, deployment, serving, monitoring, logging, and model operations.
Deep Learning System Design: A Checklist, Part I
A practical checklist for the early stages of a deep learning system: data, modeling, evaluation, training, and experiment tracking.
Neural Network Applied: Optimizer Selection
A practical guide to choosing SGD, momentum, RMSProp, Adam, AdamW, and related optimizers for neural network training.
Needle: High-performance DL System
A Deep Learning framework with customized GPU and CPU backend in C++ and Python
Motion Prediction with Guided Diffusion
Researched and developed a classifier-free guidance-based latent diffusion model for autonomous vehicle motion forecasting using UNet and Transformer as backbones
Starlink Tracking
A small D3.js-powered Satellite Tracking visualization
Travel Planner
A GPT-powered web application to help users automate travel plan suggestion, generation and archiving
Twitch+
A Search & Recommendation Engine for Twitch Streaming Video Resources
About
About Me I\'m Zhenlin Wang Criss . I graduated as an MS student from Machine Learning Department @ Carnegie Mellon University https://www.ml.cmu.edu/ . I have a strong passion for ...
Code Analyzer
C++ based code static program analyzer
More on Model Deployment
A practical overview of model deployment patterns, artifact promotion, online and batch serving, rollout strategies, rollback, and production monitoring.
Variational Inference
A practical overview of variational inference, approximate posteriors, KL divergence, ELBO, mean-field assumptions, and the connection to VAEs.
Stats in ML: Dirichlet Distribution
A practical explanation of the Dirichlet distribution, its relationship to categorical probabilities, conjugacy with the multinomial, and why it appears in topic models.
An Overview of Hidden Markov Models and Their Algorithms
A practical overview of hidden Markov models, including states, observations, transition probabilities, emission probabilities, forward-backward, Viterbi, and Baum-Welch.
SmartMall Discounted Electronic Shopping
A robust online shopping app with various middlewares serving the microservices architecture
Ensemble Models: Boosting Techniques
A practical explanation of boosting, including AdaBoost, gradient boosting, XGBoost-style regularization, learning rate, tree depth, and common pitfalls.
Variational Autoencoder (VAE)
A practical explanation of variational autoencoders, latent variables, the encoder-decoder structure, reconstruction loss, KL regularization, and sampling.
Ensemble Models: Bagging Techniques
A practical explanation of bagging, bootstrap sampling, random forests, out-of-bag evaluation, variance reduction, and when bagging helps.
Reinforcement Learning: Theoretical Foundations, Part IV
A practical introduction to policy-gradient methods, stochastic policies, the policy-gradient objective, baselines, and variance reduction.
Reinforcement Learning: Theoretical Foundations, Part V
A practical overview of actor-critic methods, deep reinforcement learning, replay buffers, target networks, PPO-style updates, and evaluation concerns.
Ensemble Models: Overview
A practical overview of ensemble learning, including bagging, boosting, stacking, voting, variance reduction, bias reduction, and common tradeoffs.
Reinforcement Learning: Theoretical Foundations, Part III
A practical guide to dynamic programming, policy evaluation, policy improvement, value iteration, and Q-learning.
Reinforcement Learning: Theoretical Foundations, Part II
A practical explanation of Markov decision processes, transition dynamics, rewards, policies, value functions, and Bellman equations.
Reinforcement Learning: Theoretical Foundations, Part I
A practical introduction to reinforcement learning concepts: agent, environment, state, action, reward, policy, return, and the exploration-exploitation tradeoff.
Gradient Descent Algorithm and Its Variants
A practical explanation of gradient descent, stochastic gradient descent, mini-batch training, momentum, adaptive learning rates, and common optimization issues.
SQL: Going Into Applications With MySQL and MongoDB
A practical comparison of relational and document databases in application development, with notes on schemas, queries, transactions, and data modeling.
The Data Mining Trilogy III: Analysis
A practical guide to exploratory data analysis: distributions, relationships, missingness, outliers, leakage checks, segmentation, and communicating findings.
SQL: Index and Optimization
A concise guide to SQL indexes, query plans, filtering, joins, aggregation, and practical optimization habits.
SQL: Pick Up the Basics Within a Day
A concise SQL primer covering SELECT, filtering, joins, aggregation, subqueries, inserts, updates, deletes, and practical query habits.
CLI-nic
Java-based medical resource management application
Database Intro
A compact introduction to databases, covering relational systems, NoSQL systems, transactions, schemas, indexes, and when each storage pattern fits.
A Regex Tutorial
Learn to process string operations in an efficient way
A Fundamental Course for Data Engineering
A practical introduction to data engineering fundamentals: ingestion, storage, batch and streaming processing, orchestration, data quality, governance, and serving.
Apache Spark: Only the Simple Answer
A simple explanation of Apache Spark: distributed data processing, DataFrames, lazy evaluation, transformations, actions, partitioning, and common performance mistakes.
Recommender Systems III: Deep Learning Methods
A practical overview of deep learning methods for recommender systems, including embeddings, two-tower retrieval, ranking models, sequence models, and evaluation.
Recommender Systems II: Factorization Machines
A practical explanation of factorization machines, feature interactions, sparse data, and why they are useful in recommendation and click prediction.
Recommender Systems I: Content-Based and Collaborative Filtering
A practical introduction to content-based recommendation, collaborative filtering, user-item matrices, similarity, cold start, and evaluation.
Dimensionality Reduction: Life Savers
A practical guide to dimensionality reduction, including PCA, t-SNE, UMAP, autoencoders, feature selection, and how to choose the right method.
Unsupervised Learning: Measures About Clustering
A practical guide to evaluating clustering with silhouette score, Davies-Bouldin index, Calinski-Harabasz score, external labels, stability, and business usefulness.
Clustering: Apriori
A practical introduction to Apriori and association rule mining, including support, confidence, lift, frequent itemsets, and market-basket analysis.
Clustering: Affinity Propagation
A concise explanation of affinity propagation, exemplars, similarity messages, preferences, damping, and practical limitations.
Clustering: DBSCAN
A practical guide to DBSCAN, density-based clustering, epsilon, minimum samples, noise points, and when density clustering is useful.
Clustering: Hierarchical, BIRCH, and Spectral
A practical overview of hierarchical clustering, BIRCH, and spectral clustering, with guidance on when each method is useful.
Clustering: K-Means and Gaussian Mixture Models
A practical comparison of K-means and Gaussian mixture models, including assumptions, distance, soft assignments, initialization, and evaluation.
An Overview of Big Data Analytics
A concise overview of big data analytics: batch and streaming workloads, descriptive and predictive analysis, data quality, storage, compute, and communication.
A Brief Intro to A/B Testing
A practical introduction to A/B testing: hypotheses, metrics, randomization, sample size, statistical significance, and common experiment pitfalls.
The Data Mining Trilogy II: Cleaning
A practical guide to cleaning data: missing values, duplicates, outliers, inconsistent categories, schema checks, and reproducible cleaning pipelines.
The Data Mining Trilogy I: Preparation
A practical overview of data preparation: defining the problem, collecting data, building schemas, splitting datasets, and preventing leakage.
Topic Modeling With Latent Dirichlet Allocation
A practical introduction to topic modeling with LDA, including bag-of-words, document-topic distributions, topic-word distributions, preprocessing, and evaluation.
Hyperparameter Tuning
A practical guide to hyperparameter tuning with search spaces, validation design, random search, Bayesian optimization, early stopping, and experiment tracking.
Feature Selection and Model Selection
A practical guide to selecting features, choosing models, avoiding leakage, comparing validation results, and balancing accuracy with complexity.
Some Supervised Learning Models
A practical overview of supervised learning models, including linear models, trees, ensembles, support vector machines, nearest neighbors, and neural networks.
Regression Models: GAM, GLM, and GLMM
A concise explanation of generalized linear models, generalized additive models, and generalized linear mixed models, with guidance on when to use each.
Model Validations and Performance Evaluators
A practical guide to validation splits, cross-validation, classification and regression metrics, calibration, slice evaluation, and model comparison.
Regression Models: Logistic Regression
A practical introduction to logistic regression for binary classification, odds, probabilities, regularization, thresholds, and evaluation.
Regression Models: Linear Regression and Regularization
A practical guide to linear regression, assumptions, loss, ordinary least squares, ridge, lasso, elastic net, and model evaluation.
MyPal
A Relationship Management System