A retention-aware review mechanism that tracks mastered prompts and periodically reintroduces them to periodically reintroduces them to the model of previous solutions, demonstrating robust generalizability across modalities and algorithms.
Chuan-Yu Qin, Chenxu Yang, Qing-Yi Si et al.· arXiv.org· 1 citation
CompassOPD is proposed, which removes this offset and transfers the within-family shift, while a frozen student reference anchors updates to the student's initial policy, and shows that CompassOPD consistently outperforms standard cross-family OPD.
Nai-Bin Gu, Qing-Yi Si, Chen-Xu Yang et al.· 0 citations
CoRe-MoE is proposed, a Compact Reusable MoE framework for parameter-efficient continual multimodal instruction tuning that improves final average performance over the strongest competing baseline by up to 5.90 points, while using less than 1% of the trainable parameters required by sequential LoRA for later tasks.
Run-Ze Liu, Nai-Bin Gu, Ming-Xu Ai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.