Showing 2026 · cs.LGShow all
2 papers · 2 filters
cs.LG2026
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
Augustinas Jučas, Yangchen Pan
Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task. Existing cold-start me…
cs.LG2026
Gradient Residual Connections
Yangchen Pan, Qizhen Ying, Philip Torr +1
Existing work has linked properties of a function's gradient to the difficulty of function approximation. Motivated by these insights, we study how gradient information can be leve…