Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning
"遗忘问题" 相关文章
Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs
Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models
[程序员] 我记性很差，程序员是不是都这样？
[程序员] 我记性很差，程序员是不是都这样？
Toward a Holistic Approach to Continual Model Merging
DOTA: Distributional Test-Time Adaptation of Vision-Language Models
SFT远不如RL？永不过时的剃刀原则打开「终身学习」大模型训练的大门
Task-Focused Consolidation with Spaced Recall: Making Neural Networks learn like college students
Continual Reinforcement Learning by Planning with Online World Models
Catastrophic Forgetting Mitigation Through Plateau Phase Activity Profiling
开源模型突破原生多模态大模型性能瓶颈，上海AI Lab代季峰团队出品
