feat: publish alignment deep dive

This commit is contained in:
wuyang
2026-07-29 06:07:42 +08:00
parent a030de41fa
commit 8378e2a741
22 changed files with 3463 additions and 35 deletions
+29 -1
View File
@@ -12,6 +12,7 @@ const routes: Record<string, string> = {
"pretraining/data": "/pretraining/data/",
moe: "/moe/",
"long-context": "/long-context/",
"post-training/alignment": "/post-training/alignment/",
reasoning: "/reasoning/",
"training-systems": "/training-systems/",
"systems/numerics": "/systems/numerics/",
@@ -88,6 +89,7 @@ const paths = [
<a class="button" href="/pretraining/data/">数据工程专题</a>
<a class="button" href="/moe/">MoE 专题</a>
<a class="button" href="/long-context/">长上下文专题</a>
<a class="button" href="/post-training/alignment/">后训练与偏好专题</a>
<a class="button" href="/reasoning/">推理专题</a>
<a class="button" href="/training-systems/">训练系统专题</a>
<a class="button" href="/systems/numerics/">数值与优化专题</a>
@@ -100,7 +102,7 @@ const paths = [
<div class="hero-stats">
<div><b>16</b><span>核心专题</span></div>
<div><b>151</b><span>K3 报告来源</span></div>
<div><b>258</b><span>关键论文索引</span></div>
<div><b>280</b><span>关键论文索引</span></div>
<div><b>47p</b><span>K3 技术报告</span></div>
</div>
</aside>
@@ -114,6 +116,22 @@ const paths = [
<section class="section compact release-section" id="new-chapters">
<div class="release-grid">
<a class="release-card alignment-release" href="/post-training/alignment/">
<div>
<p class="eyebrow"><span>NEW / CHAPTER 10</span> ALIGNMENT · PREFERENCE</p>
<h2>DPO 没有“消灭 RLHF”,RLHF 也不等于只跑一次 PPO</h2>
<p>
用目标、监督、来源、SFT、偏好、奖励、更新、分布、约束、失效与证据十二张账,
从 2017 人类偏好学习一路走到 InstructGPT、Constitutional AI、DPO、DeepSeek-R1/V4 与 Kimi K3。
</p>
</div>
<dl>
<div><dt>LINEAGE</dt><dd>2017 → 2026</dd></div>
<div><dt>PAPERS</dt><dd>44 个一手节点</dd></div>
<div><dt>LAB</dt><dd>SFT · RM · PPO/DPO · 配方比较</dd></div>
</dl>
<span class="release-arrow" aria-hidden="true">从 Base Model 进入可协作助手 →</span>
</a>
<a class="release-card transformer-release" href="/foundations/">
<div>
<p class="eyebrow"><span>NEW / CHAPTER 02</span> ATTENTION · TRANSFORMER</p>
@@ -491,6 +509,7 @@ const paths = [
transition: transform 180ms ease, border-color 180ms ease;
}
.alignment-release,
.transformer-release,
.foundation-release,
.numerics-release,
@@ -502,6 +521,14 @@ const paths = [
min-height: 510px;
}
.alignment-release {
background:
radial-gradient(circle at 82% 18%, rgba(134, 76, 76, 0.2), transparent 30%),
radial-gradient(circle at 62% 74%, rgba(76, 118, 112, 0.11), transparent 28%),
repeating-linear-gradient(90deg, transparent 0 72px, rgba(134, 76, 76, 0.04) 72px 73px),
var(--paper-raised);
}
.numerics-release {
background:
radial-gradient(circle at 82% 18%, rgba(113, 82, 137, 0.2), transparent 30%),
@@ -616,6 +643,7 @@ const paths = [
padding-bottom: 76px;
}
.alignment-release,
.transformer-release,
.foundation-release,
.numerics-release,