Random Initialization of Gated Sparse Adapters
"灾难性遗忘" 相关文章
GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
Thinking Machine新研究刷屏！结合RL+微调优势，小模型训练更具性价比了
Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
Knowledge-guided Continual Learning for Behavioral Analytics Systems
Meta拆掉AI持续学习路上的最大炸弹，“微调”又有了一战之力
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
Continual Knowledge Adaptation for Reinforcement Learning
Continual Knowledge Adaptation for Reinforcement Learning
大模型微调范式认知再被颠覆？UIUC、Amazon团队最新研究指出SFT灾难性遗忘问题或被误解
大模型微调范式认知再被颠覆？UIUC、Amazon团队最新研究指出SFT灾难性遗忘问题或被误解
大模型微调范式认知再被颠覆？UIUC、Amazon团队最新研究指出SFT灾难性遗忘问题或被误解
大模型微调范式认知再被颠覆？UIUC、Amazon团队最新研究指出SFT灾难性遗忘问题或被误解
大模型微调范式认知再被颠覆？UIUC、Amazon团队最新研究指出SFT灾难性遗忘问题或被误解
STABLE: Gated Continual Learning for Large Language Models
Continual Learning via Sparse Memory Finetuning
Continual Learning via Sparse Memory Finetuning
大语言模型的遗忘也许是一个悖论？清华团队揭示Unlearning技术的两难困境
大语言模型的遗忘也许是一个悖论？清华团队揭示Unlearning技术的两难困境
大语言模型的遗忘也许是一个悖论？清华团队揭示Unlearning技术的两难困境
