Attention 原论文其实谈过 MLP 与注意力关系,但只写在 arXiv v2/v3 版本里
CatAstro_Piyush · x · 2026-10-17
In a thread arguing that every layer is a memory layer whose capacity can be estimated via heuristic interference-suppression arguments, heyyalexwang points out that the original attention paper actually discussed the relationship between MLPs and attention.
The catch: that discussion only appeared in arXiv versions v2 and v3 — the paper is now on v7, so the passage is no longer visible in the latest version.
「研究」频道最新
- IFM 开源 RL360:8192 并发沙箱、130 万 rollouts 的 RL 基建 — rupspace · 2026-10-23
- AI 揭穿阴谋论研究风波落幕：Science 撤回关注声明，结论不变 — DG_Rand · 2026-10-23
- Embodied First Exam：一行代码在 44 台机器人上考你的 Agent — ManlingLi_ · 2026-10-23
- Anima Anandkumar 演讲：AI 气象模型胜超算，但不会取代科学家 — AnimaAnandkumar · 2026-10-23
- GLM-5.3-Flash 实现 1M token 上下文训练，较基线提升 64 倍 — AndrewLBeam · 2026-10-23
- 作者用布尔逻辑造 LM:前向传播单线程仅需几微秒但训练极慢 — cephaloform · 2026-10-23