Blog

A collection of articles on AI research, implementation, and insights.

Model-Based RL

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 11. Model-Based RL

RL for LLMs - Preference Optimization

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 9. RL for LLMs:Preference Optimization

Reward Learning

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 8. Reward Learning

Offline RL

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 7. Offline RL

Non Parametric Few-Shot Learning

Lecture

CS330

Summary of lecture CS330 (2022) Lecture 6. Non Parametric Few-Shot Learning

Q-Learning

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 6. Q-Learning

Optimization-Based Meta-Learning

Lecture

CS330

Summary of lecture CS330 (2022) Lecture 5. Optimization-Based Meta-Learning

Off-Policy Actor-Critic Methods

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 5. Off-Policy Actor-Critic Methods

Black-Box Meta-Learning & In-Context Learning

Lecture

CS330

Summary of lecture CS330 (2022) Lecture 4. Black-Box Meta-Learning & In-Context Learning

Actor-Critic Methods

Lecture

CS224R

Summary of lecture CS224R (2025) Lecture 4. Actor-Critic Methods

Transfer Learning & Fine-tuning

Lecture

CS330

Summary of lecture CS330 (2022) Lecture 3. Transfer learning & Fine-tuning

Multi-task learning

Lecture

CS330

Summary of lecture CS330 (2022) Lecture 2. Multi-task learning

retrospective of 2025

Life

Reflections on 2025 - Achievements, Regrets, and Resolutions

Experiences I had while doing Vibe Coding

GenAI

Life

My experience using ChatGPT and Gemini Code Assist (Agent Mode)

Taylor Expansion

python

numpy

math

Applying Taylor Expansion in various functions.