Back to Homepage

Articles

Long-form explainers, short technical notes, and paper commentary across Towards Data Science and X Articles.

Article Links

X Article Harness Evaluations

How to design experiments that evaluate agentic harnesses, not just isolated model calls.

Evaluation
Towards Data Science How Vision Language Models Are Trained from "Scratch"

A deep dive into exactly how text-only language models are fine-tuned to see images.

Vision Language Models
X Article Agentic Harness Engineering

A practical method for building agentic harnesses: scoped workflows, tool boundaries, evaluation loops, and failure handling.

Agentic AI
Towards Data Science How to Build Your Own Custom LLM Memory Layer from Scratch

Step-by-step guide to building autonomous memory retrieval systems.

LLM Memory
X Article Recursive Language Models

A compact explanation of Recursive Language Models and why recursive structure can help with long-context reasoning.

Recursive LMs
X Article Diffusion Language Models

An introduction to diffusion language models: how they generate text differently, where they fit, and when they are worth considering.

Language Models
X Article Speculative Decoding (SD)

A practical explanation of speculative decoding for LLM inference: draft models, verification, and why it can speed up generation.

Inference
Towards Data Science The Reinforcement Learning Handbook: A Guide to Foundational Questions

Simplifying the concepts required to master reinforcement learning.

Reinforcement Learning
Towards Data Science PyTorch Explained: From Automatic Differentiation to Training Custom Neural Networks

A practical introduction to deep learning internals through PyTorch.

PyTorch
Towards Data Science Context Engineering - A Comprehensive Hands-On Tutorial with DSPy

A hands-on walkthrough of context engineering, one module at a time.

DSPy
Towards Data Science How to Fine-Tune Small Language Models to Think with Reinforcement Learning

A visual tour and from-scratch guide to train GRPO reasoning models in PyTorch.

Reasoning Models
Towards Data Science Sesame Speech Model: How This Viral AI Model Generates Human-Like Speech

Residual vector quantizers, conversational speech AI, and talkative transformers.

Speech AI
Towards Data Science The Ultimate Guide to RAGs - Each Component Dissected

A visual tour of what it takes to build strong retrieval-augmented LLM pipelines.

RAG
Towards Data Science The Evolution of Text to Video Models

Simplifying the neural networks behind generative video diffusion.

Video Diffusion
Towards Data Science Segment Anything 2: What Is the Secret Sauce? (A Deep Learner's Guide)

How foundation, promptable, interactive, and video segmentation fit together.

Computer Vision
X Paper Review SDPO

A paper review of Self-Distillation with Policy Optimization, covering how models can improve by generating and learning from their own preference signal.

Post-training
X Paper Review Minimax M2.5 Training

A review of Minimax M2.5 post-training, with emphasis on asynchronous RL, scaling training throughput, and reasoning-model optimization.

Async RL
X Paper Review GLM 5.1 Training

A paper-review breakdown of GLM-5 training: pretraining, post-training, reasoning behavior, and the engineering choices behind the model family.

Model Training
X Paper Review Deep Research Agents

A paper review on training smaller deep-research agents that can search, synthesize, cite, and iteratively improve research workflows.

Research Agents
X Paper Review HyperAgents

A review of HyperAgents, a Darwin-Godel-inspired framework for agents that evolve skills, tools, and strategies through self-improvement loops.

Self-improving AI
X Paper Review Meta Harness

A paper review of self-improving AI systems that combine auto-research, code evolution, and harness-level feedback to improve agent behavior.

Auto-research
X Paper Review Skill Curation for Self-Evolving Agents

A review of Google's SkillOS work and the role of skill curation in making self-evolving agents more reliable and reusable.

SkillOS