谢赛宁·· 2025-08-11精选
this isn’t just a modeling problem. it’s also a benchmarking problem. spurious correlations are alw...
this isn’t just a modeling problem. it’s also a benchmarking problem. spurious correlations are alw...
AI 导读
这不只是建模问题。也是基准测试问题。
推荐理由
当前多模态模型靠语言捷径'作弊',真实场景落地将暴露致命隐患
来源:谢赛宁 · x.com