My Neuro-Symbolic Meta-Policies paper was accepted at ISWC 2026
Why I want agents to choose their memory rules, not hide them
Taewoon Kim
AI researcher and engineer.
Latest posts
My Co-Learning paper was accepted at RO-MAN 2026
Why I want a robot to remember how a team worked before
My KG Memory Transfer paper was accepted at RLC 2026
Why I care about learning which symbolic facts should persist
Building embedded Python bindings for ArcadeDB
Why I wanted a lightweight, local-first way to use ArcadeDB from Python
What Is a Knowledge Graph? A Practical Guide Across RDF and Property Graphs
Formal basics, real systems, and why industry favors property graphs while RDF remains important
From REINFORCE to PPO: The Complete On-Policy RL Journey
Understanding the evolution from basic policy gradients to modern LLM fine-tuning algorithms
From VAEs to Diffusion Models: A Step-by-Step Journey
Understanding the evolution of generative models through practical implementations
Discrete vs. Continuous: A Tale of Two Approaches to Language Modeling
Balancing n-gram models and neural networks for next-token prediction
RL vs SL: Understanding Their Roles in Large Language Models
Bridging Reinforcement Learning and Supervised Learning in LLMs
Understanding Maximum Likelihood Estimation
A Deep Dive into MLE, Loss Functions, and Beyond
Sequential Decision-Making with Transformers
Offline RL, Behavior Cloning, and The Magic of Sequence Modeling
From 1+1 in Assembly to LLMs: The Evolution of Computing Abstraction
Tracing the Layers from Machine Code to Natural Language Interfaces
The Problems with p-values
Why Frequentist Significance Testing Falls Short
Can the Transformer be viewed as a special case of a Graph Neural Network (GNN)?
A natural language text can be seen as a knowledge graph
Is supervised learning a special type of reinforcement learning?
The reason why reinforcement learning is such a hard problem
Playing around with Hugging Face Llama 3.1 locally
4bit quantization is amazing
Training a GCN-based edge classifier
Exploring the challenges and strategies for effective edge classification with graph neural networks (GNNs)
A machine with human-like memory systems
Can machines think like us?
Using ChatGPT is just so great
This really can do a lot of things, although it's still biased.
My new website
My boring old website had to be gone.
Bloom: A 176b-parameter open-access multilingual language model
Unlocking the power of open-source language models
Room classifier
A simple room classifier made using EfficientNet and PyTorch Lightning
Promptsource: An integrated development environment and repository for natural language prompts
Revolutionizing NLP with a collaborative hub for crafting and sharing prompts
IGLU: interactive grounded language understanding in a collaborative environment
We won the NeurIPS 2021 competition
Multitask prompted training enables zero-shot task generalization
Achieving superior zero-shot generalization through explicit multitask prompting
EmoBERTa: Speaker-aware emotion recognition in conversation with RoBERTa
Achieving state-of-the-rrt emotion recognition in conversations with a simple RoBERTa-based approach
Generalizing MLPs with dropouts, batch normalization, and skip connections
A simple age-gender classification model using Arcface embeddings and MLPs