为贝叶斯推断提供测试时校准引导，显著提升不确定性量化精度，附开源代码。
arXiv:2602.22428v2 Announce Type: replace-cross Abstract: Test-time guidance is a widely used mechanism for steering pretrained diffusion models towar…
大模型并非真贝叶斯，而是在期望上趋同，这一视角颠覆传统认知，值得细读。
arXiv:2507.11768v3 Announce Type: replace-cross Abstract: Bayesian accounts of in-context learning face a direct objection: exact posterior predictive…
人类在长期规划任务中依然优于AI，概率公式揭示优化难度随目标值非线性增长，值得关注。
Article URL: https://joyemang33.github.io/blog/2026/humans-dont-just-sample/ Comments URL: https://news.ycombinator.com/item?id=48564319 Points: 2 # C…