Pith. sign in

Ss-il: Separated softmax for incremental learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Scalable Strategies for Continual Learning with Replay

cs.LG · 2025-05-18 · conditional · novelty 6.0

A replay-based continual learning toolkit that combines low-rank adaptation, a post-task consolidation phase, and sequential weight merging to cut replay sample usage by up to 65% at matched accuracy.

citing papers explorer

Showing 1 of 1 citing paper.

  • Scalable Strategies for Continual Learning with Replay cs.LG · 2025-05-18 · conditional · none · ref 1

    A replay-based continual learning toolkit that combines low-rank adaptation, a post-task consolidation phase, and sequential weight merging to cut replay sample usage by up to 65% at matched accuracy.