1
A Gravitational Interpretation of Fine-Tuning Reversion
重磅发现：无害数据微调竟能部分逆转模型训练行为，AI安全可能悄然瓦解——引力视角下的精细调谐逆转。
arXiv:2606.28525v1 Announce Type: new Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can ero…