This work proposes Retention-aware Policy Optimization (RaPO), a simple yet effective RFT method that mitigates forgetting through trajectory-level reward shaping, and comprehensively evaluates RaPO across five visual continual learning settings.
This paper presents a novel sparsity-driven continual learning framework that operates in two stages: it first identifies a sparse, task-critical parameter mask via a sparsity-inducing objective, then performs mask-constrained fine-tuning by only optimizing parameters selected by the mask.
Yunxiang Fu, Meng Lou, Zicheng Liao et al.· 1 citation
Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze loca...
FACET proposes an efficient replay-free task-conditioned feature consistency loss, aiming to mitigate catastrophic forgetting of the learned mixture distribution in the adapter's feature space, and demonstrates robust scalability.
Yunxiang Fu, Meng Lou, Yizhou Yu· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
