June 25, 2024
Reverse-Process Synthetic Data Generation for Math Reasoning
Training LLMs on mathematical reasoning by inverting easy-to-solve problems: generate derivatives, reverse them into integration exercises with full step-by-step solutions.
Browse posts by category
Training LLMs on mathematical reasoning by inverting easy-to-solve problems: generate derivatives, reverse them into integration exercises with full step-by-step solutions.
An eBook metadata management tool with a SQLite backend, knowledge graphs, semantic search, and MCP server integration. Part of the Long Echo project.
A plugin-based system for importing, storing, searching, and exporting AI conversations from multiple providers in a unified tree format. Part of the Long Echo project.
A logic programming system that alternates between wake and sleep phases, using LLMs for knowledge generation during wake and compression-based learning during sleep.