Learning as Approximation
A learning note on the shared correction pattern behind gradient descent, temporal difference learning, stochastic approximation, and Bellman fixed-point methods.
AIReinforcement LearningOptimizationStochastic Approximation
Xingyu (Eric) Yang
CS, Monash University
AI is the research direction I want to grow into for the long run. I am especially drawn to representation learning, explainability, language, and the mathematical structure behind learning systems. I build tools around my reading and notes because I think better when ideas become inspectable.
Connect
Research Interests
01Cross-modal representation learninghow vision, language, sound, and geometry can share structure
02Explainability and interpretabilityhow model behavior becomes readable
03Ontological systems and world modelshow entities, relations, and abstractions are organized
04Mathematical and linguistic foundationshow formal systems, proof, semantics, and learning theory meet
This site
A research notebook and public second brain for representation, explanation, language, and the mathematical structure underneath learning systems.
A personal portal and an open research notebook at once: who I am, what I care about, and how I think. Still growing.
Recent Writing
Recent entries
My Personal AI Workbench: How I Split Work Between Codex, Hermes, Obsidian, and CC Switch
A concrete design note on my personal AI workbench: owners, state flows, cron maintenance, instruction boundaries, and a Karpathy-style Obsidian second brain adapted for daily work.
AI WorkflowMulti-Agent SystemPersonal Knowledge ManagementObsidian
From Noise to Images: A Short History of Diffusion Models
A learning-oriented overview of how diffusion models moved from probabilistic denoising to practical visual-generation systems.
AIDiffusion ModelComputer VisionGenerative AI
Artificial Intelligence
The artificial-intelligence note index for learning maps and field histories: how key model families came to be and why their designs took the shape they did.
From Words to Attention: How I Learned to See Transformers
A short learning note on how word representations led to attention, self-attention, and Transformers.
AITransformerAttentionNLP