AIBullisharXiv – CS AI · Mar 56/10
🧠
Test-Time Meta-Adaptation with Self-Synthesis
Researchers introduce MASS, a meta-learning framework that enables large language models to self-adapt at test time by generating synthetic training data and performing targeted self-updates. The system uses bilevel optimization to meta-learn data-attribution signals and optimize synthetic data through scalable meta-gradients, showing effectiveness in mathematical reasoning tasks.