AI 导读
– https://t.co/rBWwIlj9Id 标题："Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs"
正文
– https://t.co/rBWwIlj9Id
Title: "Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs"
来源：@rohanpaul_ai · x.com