queirozf.com

paper-summary instruction-tuning language-modeling

Paper Summary: KTO: Model Alignment as Prospect Theoretic Optimization

21 Jul 2025   Summary of the 2024 article "KTO: Model Alignment as Prospect Theoretic Optimization" AKA the KTO paper by Ethayarajh et al.

Read More ›

paper-summary instruction-tuning language-modeling

Paper Summary: A General Theoretical Paradigm to Understand Learning from Human Preferences

21 Jul 2025   Summary of the 2023 article "A General Theoretical Paradigm to Understand Learning from Human Preferences" (AKA the IPO paper) by Azar et al.

Read More ›

paper-summary language-modeling instruction-tuning

Paper Summary: Fine-Tuning Language Models from Human Preferences

20 Jul 2025   Summary of the 2019 article "Fine-Tuning Language Models from Human Preferences" by Ziegler et al.

Read More ›

real-time-machine-learning

Practical Tips for more Robust Real-time ML models

09 Jul 2025   Quick introduction and some practical tips on how to make a real-time ML model more robust and less sensitive to changes in features at inference time.

Read More ›

trino

String Manipulation Function in Trino/PrestoSQL: Reference and Examples

23 Jun 2025   Commonly-used string manipulation functions in Trino/PrestoSQL.

Read More ›

paper-summary language-modeling reasoning

Paper Summary: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

15 Jun 2025   Summary of the 2022 article "Chain-of-Though Prompting Elicits Reasoning in Large Language Models" by Wei et al.

Read More ›

paper-summary sequence-learning recurrent-neural-networks

Paper Summary: Learning to Forget: Continual Prediction with LSTM

31 May 2025   Summary of the 1999 article "Learning to Forget: Continual Prediction with LSTM" by Gers et al.

Read More ›

testing software-engineering software-architecture

Why Test Software? TL;DR Summary

27 Apr 2025   Minimum Viable Post to send to your colleague who isn't sure whether tests are really needed.

Read More ›

paper-summary language-modeling reinforcement-learning

Paper Summary: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

19 Apr 2025   Summary of the 2025 article "DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning" by DeepSeek AI.

Read More ›

apache-pinot

Manipulating Datetime Values in Apache Pinot: Reference and Examples

17 Apr 2025   Examples on how to manipulate and format datetime and datetime-like values in Apache Pinot.

Read More ›