MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

MIT researchers unveil a new fine-tuning method that lets enterprises consolidate their "model zoos" into a single, continuously learning agent.
IEEE

Query-Sparsified Transformer with Adapter Tuning for Log-Based Anomaly Detection

Abstract: Log anomaly detection is critical for ensuring the reliability and security of large-scale computer systems. Existing approaches, including rule-based, statistical, and deep learning methods ...
GitHub

SQL Query Plan Visualizer

Typical database query plans are dense, text-heavy, and hard to read. SQL Query Plan Visualizer turns them into intuitive, directed graphs (DAGs) that let you instantly spot performance bottlenecks.
GitHub

LLM Agents & Ecosystem Handbook

A polished, curated collection of Large Language Model (LLM) agents, tutorials and ecosystem insights. This handbook highlights projects that push the boundaries of generative AI, multi-agent ...