#artificial intelligence
Sep 2026
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
This work derives a token- and layer-wise decomposition of how learning from one token changes another prediction, and connects data attribution, forgetting, and plasticity loss as distinct regimes of the same evolving learning dynamics.
Yi Ren, Wen-Long Deng, Guan-Zhe Hong et al.
· arXiv.org · 1 citation