This repository collects and organizes research papers on instruction-tuning, a training approach that teaches language models to follow natural language instructions across multiple tasks. The collection traces the evolution of the field from foundational works like Natural-Instruction (ACL 2022), FLAN (ICLR 2022), and T0 (ICLR 2022) through subsequent research. It serves as a reference resource for researchers and practitioners studying multi-task generalization and zero-shot learning in large language models.