feat: publish native multimodal chapter

src/components/SiteHeader.astro

@@ -17,6 +17,7 @@ const items = [
   { id: "alignment", href: "/post-training/alignment/", label: "后训练" },
   { id: "reasoning", href: "/reasoning/", label: "推理" },
   { id: "agents", href: "/agents/", label: "Agent" },
+  { id: "multimodal", href: "/multimodal/", label: "多模态" },
   { id: "training-systems", href: "/training-systems/", label: "训练系统" },
   { id: "numerics", href: "/systems/numerics/", label: "数值" },
   { id: "papers", href: "/papers/", label: "论文库" },

src/data/chapters.ts

@@ -190,12 +190,12 @@ export const chapters: Chapter[] = [
     title: "原生多模态",
     kicker: "MULTIMODAL",
     question: "图像是外接插件，还是和文字一样的第一类输入？",
-    summary: "从 ViT/CLIP、连接器式 VLM 走到 Kimi-VL、MoonViT-V2 与统一主干。",
-    status: "queued",
-    progress: 11,
-    papers: 19,
+    summary: "用十六张账串起视觉 Token、CLIP、连接器、高分辨率、OCR、视频、统一理解生成，并重点拆解 DeepSeek 三分支与 Kimi 三代 MoonViT。",
+    status: "published",
+    progress: 76,
+    papers: 55,
     prerequisites: ["02"],
-    highlights: ["ViT", "视觉 Token", "MoonViT-V2"],
+    highlights: ["DeepSeek 三分支", "Kimi 三代 MoonViT", "四联实验"],
   },
   {
     number: "14",

src/data/papers.ts

@@ -2416,6 +2416,22 @@ export const papers: Paper[] = [
     contribution: "面向 Agentic AI 的 Firecracker microVM 环境，支持 pause、resume、fork、snapshot 与高密度运行。",
     verified: true,
   },
+  {
+    year: 2012,
+    title: "ImageNet Classification with Deep Convolutional Neural Networks",
+    url: "https://proceedings.neurips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks",
+    topics: ["多模态"],
+    contribution: "AlexNet 以 GPU、大规模卷积网络与 ImageNet 监督推动可扩展视觉表示。",
+    verified: true,
+  },
+  {
+    year: 2015,
+    title: "Deep Residual Learning for Image Recognition",
+    url: "https://arxiv.org/abs/1512.03385",
+    topics: ["多模态", "Transformer"],
+    contribution: "残差连接让更深视觉骨干稳定优化，成为多模态视觉塔的重要前史。",
+    verified: true,
+  },
   {
     year: 2020,
     title: "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale",
@@ -2424,6 +2440,14 @@ export const papers: Paper[] = [
     contribution: "ViT 把图像 patch 视为 Token 输入 Transformer。",
     verified: true,
   },
+  {
+    year: 2021,
+    title: "Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision",
+    url: "https://arxiv.org/abs/2102.05918",
+    topics: ["多模态", "数据", "Scaling"],
+    contribution: "ALIGN 用超大规模噪声 web 图文对训练双编码器，展示数据规模路线。",
+    verified: true,
+  },
   {
     year: 2021,
     title: "Learning Transferable Visual Models From Natural Language Supervision",
@@ -2432,6 +2456,30 @@ export const papers: Paper[] = [
     contribution: "CLIP 以海量图文对比学习建立可迁移视觉语义空间。",
     verified: true,
   },
+  {
+    year: 2021,
+    title: "Multimodal Few-Shot Learning with Frozen Language Models",
+    url: "https://arxiv.org/abs/2106.13884",
+    topics: ["多模态"],
+    contribution: "Frozen 用视觉编码器生成连续前缀，连接冻结语言模型并激活多模态 in-context learning。",
+    verified: true,
+  },
+  {
+    year: 2021,
+    title: "LiT: Zero-Shot Transfer with Locked-image Text Tuning",
+    url: "https://arxiv.org/abs/2111.07991",
+    topics: ["多模态", "后训练"],
+    contribution: "锁定强图像塔，只训练文本侧去匹配既有视觉空间。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation",
+    url: "https://arxiv.org/abs/2201.12086",
+    topics: ["多模态", "数据"],
+    contribution: "用 captioner 生成描述、filter 清理噪声，同时服务视觉理解与生成。",
+    verified: true,
+  },
   {
     year: 2022,
     title: "Flamingo: a Visual Language Model for Few-Shot Learning",
@@ -2448,6 +2496,134 @@ export const papers: Paper[] = [
     contribution: "用轻量 Q-Former 桥接冻结视觉编码器与 LLM。",
     verified: true,
   },
+  {
+    year: 2023,
+    title: "MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models",
+    url: "https://arxiv.org/abs/2304.10592",
+    topics: ["多模态", "后训练"],
+    contribution: "用少量高质量视觉对话对齐冻结视觉编码器与冻结语言模型。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning",
+    url: "https://arxiv.org/abs/2305.06500",
+    topics: ["多模态", "后训练"],
+    contribution: "让 Q-Former 感知指令，并系统研究跨任务视觉指令泛化。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "PaLI-X: On Scaling up a Multilingual Vision and Language Model",
+    url: "https://arxiv.org/abs/2305.18565",
+    topics: ["多模态", "Scaling"],
+    contribution: "从组件规模与多语言任务混合两轴扩展视觉—语言模型。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models",
+    url: "https://arxiv.org/abs/2305.07895",
+    topics: ["多模态", "评测"],
+    contribution: "联合评测文字识别、场景文字 VQA、文档 VQA、KIE 与手写公式。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Evaluating Object Hallucination in Large Vision-Language Models",
+    url: "https://arxiv.org/abs/2305.10355",
+    topics: ["多模态", "评测"],
+    contribution: "POPE 用轮询式对象存在性问题更稳定地诊断视觉幻觉。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Kosmos-2: Grounding Multimodal Large Language Models to the World",
+    url: "https://arxiv.org/abs/2306.14824",
+    topics: ["多模态"],
+    contribution: "用 location token 和 grounded image-text pairs 把文本指称绑定到视觉区域。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution",
+    url: "https://arxiv.org/abs/2307.06304",
+    topics: ["多模态", "训练系统"],
+    contribution: "在固定 Token 预算内打包不同分辨率与长宽比图像的 patch 序列。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "MMBench: Is Your Multi-modal Model an All-around Player?",
+    url: "https://arxiv.org/abs/2307.06281",
+    topics: ["多模态", "评测"],
+    contribution: "用双语多选、能力分层与 CircularEval 建立综合 VLM 评测。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond",
+    url: "https://arxiv.org/abs/2308.12966",
+    topics: ["多模态"],
+    contribution: "把开放视觉对话、OCR 与 grounding 能力整合进 Qwen 视觉语言路线。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Improved Baselines with Visual Instruction Tuning",
+    url: "https://arxiv.org/abs/2310.03744",
+    topics: ["多模态", "后训练"],
+    contribution: "LLaVA-1.5 用两层 MLP、更多任务数据与清晰训练配方强化简单基线。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts",
+    url: "https://arxiv.org/abs/2310.02255",
+    topics: ["多模态", "推理", "评测"],
+    contribution: "用图表、几何、函数与视觉数学题联合考察感知和多步推理。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion",
+    url: "https://arxiv.org/abs/2310.14566",
+    topics: ["多模态", "评测"],
+    contribution: "用控制组问题区分语言幻觉、视觉错觉、回答倾向与逻辑一致性。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Video-LLaVA: Learning United Visual Representation by Alignment Before Projection",
+    url: "https://arxiv.org/abs/2311.10122",
+    topics: ["多模态"],
+    contribution: "在投影前对齐图像和视频表示，探索共同视觉—语言空间。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI",
+    url: "https://arxiv.org/abs/2311.16502",
+    topics: ["多模态", "推理", "评测"],
+    contribution: "以 11.5K 大学级问题覆盖六大学科、183 子领域与 30 种图像类型。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models",
+    url: "https://arxiv.org/abs/2311.17043",
+    topics: ["多模态", "长上下文"],
+    contribution: "用内容 Token 与上下文 Token 压缩长视频视觉序列。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback",
+    url: "https://arxiv.org/abs/2312.00849",
+    topics: ["多模态", "后训练", "评测"],
+    contribution: "以 segment-level 人工纠错和 dense DPO 对齐视觉忠实度。",
+    verified: true,
+  },
   {
     year: 2023,
     title: "Visual Instruction Tuning",
@@ -2464,6 +2640,55 @@ export const papers: Paper[] = [
     contribution: "SigLIP 以成对 sigmoid loss 简化大规模图文对比。",
     verified: true,
   },
+  {
+    year: 2024,
+    title: "DeepSeek-VL: Towards Real-World Vision-Language Understanding",
+    url: "https://arxiv.org/abs/2403.05525",
+    topics: ["多模态", "数据"],
+    contribution: "面向截图、PDF、OCR 与图表，用混合视觉编码器处理高分辨率并管理模态竞争。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites",
+    url: "https://arxiv.org/abs/2404.16821",
+    topics: ["多模态", "Scaling"],
+    contribution: "InternVL 1.5 结合 6B 视觉塔、最多 40 个动态 tile 与高质量双语数据。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Chameleon: Mixed-Modal Early-Fusion Foundation Models",
+    url: "https://arxiv.org/abs/2405.09818",
+    topics: ["多模态", "Transformer"],
+    contribution: "把图像与文字离散成可交错 Token，用 early-fusion 自回归主干统一建模。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis",
+    url: "https://arxiv.org/abs/2405.21075",
+    topics: ["多模态", "评测"],
+    contribution: "用 900 段短中长视频、字幕和音频条件系统评估视频理解。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models",
+    url: "https://arxiv.org/abs/2406.09403",
+    topics: ["多模态", "推理", "Agent"],
+    contribution: "让模型画线、框选并调用视觉工具，以新视觉产物继续推理。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "SOLO: A Single Transformer for Scalable Vision-Language Modeling",
+    url: "https://arxiv.org/abs/2407.06438",
+    topics: ["多模态", "Transformer", "Scaling"],
+    contribution: "探索单一 Transformer 视觉—语言架构与可稳定训练的开放配方。",
+    verified: true,
+  },
   {
     year: 2024,
     title: "LLaVA-OneVision: Easy Visual Task Transfer",
@@ -2472,6 +2697,82 @@ export const papers: Paper[] = [
     contribution: "统一单图、多图与视频的视觉指令迁移。",
     verified: true,
   },
+  {
+    year: 2024,
+    title: "Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model",
+    url: "https://arxiv.org/abs/2408.11039",
+    topics: ["多模态", "Transformer"],
+    contribution: "在同一 Transformer 上对文字做 NTP、对连续图像表示做 diffusion。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution",
+    url: "https://arxiv.org/abs/2409.12191",
+    topics: ["多模态", "长上下文"],
+    contribution: "引入动态视觉 Token、M-RoPE 与统一图像 / 视频输入。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation",
+    url: "https://arxiv.org/abs/2410.13848",
+    topics: ["多模态"],
+    contribution: "解耦理解与生成的视觉编码路径，同时共享一个自回归主干。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation",
+    url: "https://arxiv.org/abs/2411.07975",
+    topics: ["多模态"],
+    contribution: "把语言自回归与图像 rectified flow 放进同一框架，并对齐解耦视觉表示。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling",
+    url: "https://arxiv.org/abs/2412.05271",
+    topics: ["多模态", "Scaling", "推理"],
+    contribution: "InternVL 2.5 从模型、数据与测试时配置三个轴研究多模态扩展。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding",
+    url: "https://arxiv.org/abs/2412.10302",
+    topics: ["多模态", "MoE", "长上下文"],
+    contribution: "用动态 tile、2×2 pixel shuffle、MLP adaptor、DeepSeekMoE 与 MLA 处理高分辨率输入。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling",
+    url: "https://arxiv.org/abs/2501.17811",
+    topics: ["多模态", "Scaling"],
+    contribution: "延续 Janus 解耦视觉路径，改进训练策略、数据规模与模型规模。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Qwen2.5-VL Technical Report",
+    url: "https://arxiv.org/abs/2502.13923",
+    topics: ["多模态", "Agent"],
+    contribution: "从头训练动态分辨率 ViT，引入绝对时间编码并强化文档和视觉 Agent。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models",
+    url: "https://arxiv.org/abs/2503.06749",
+    topics: ["多模态", "推理", "后训练"],
+    contribution: "探索用大规模强化学习激活多模态长思维与视觉推理。",
+    verified: true,
+  },
   {
     year: 2025,
     title: "Kimi-VL Technical Report",
@@ -2481,6 +2782,40 @@ export const papers: Paper[] = [
     spotlight: "Kimi",
     verified: true,
   },
+  {
+    year: 2025,
+    title: "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use",
+    url: "https://arxiv.org/abs/2505.19255",
+    topics: ["多模态", "推理", "Agent", "后训练"],
+    contribution: "用可验证奖励训练模型自主选择视觉工具并从新图像观察继续推理。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "DeepSeek-OCR: Contexts Optical Compression",
+    url: "https://arxiv.org/abs/2510.18234",
+    topics: ["多模态", "长上下文", "数据"],
+    contribution: "用 DeepEncoder 将二维页面压成少量视觉 Token，研究光学长上下文压缩。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2026,
+    title: "DeepSeek-OCR 2: Visual Causal Flow",
+    url: "https://arxiv.org/abs/2601.20552",
+    topics: ["多模态", "长上下文"],
+    contribution: "DeepEncoder V2 根据图像语义动态重排视觉 Token，再交给语言解码器。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
+  {
+    year: 2026,
+    title: "ToolsRL: Reward Is All Tool Learning Needs",
+    url: "https://arxiv.org/abs/2604.19945",
+    topics: ["多模态", "推理", "Agent", "后训练"],
+    contribution: "以强化学习研究视觉工具选择、调用与多步观察闭环。",
+    verified: true,
+  },
   {
     year: 2020,
     title: "Measuring Massive Multitask Language Understanding",

src/pages/index.astro

@@ -15,6 +15,7 @@ const routes: Record<string, string> = {
   "post-training/alignment": "/post-training/alignment/",
   reasoning: "/reasoning/",
   agents: "/agents/",
+  multimodal: "/multimodal/",
   "training-systems": "/training-systems/",
   "systems/numerics": "/systems/numerics/",
 };
@@ -93,6 +94,7 @@ const paths = [
           <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="/agents/">Agent 专题</a>
+          <a class="button" href="/multimodal/">原生多模态专题</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>
         </div>
@@ -104,7 +106,7 @@ 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>314</b><span>关键论文索引</span></div>
+          <div><b>355</b><span>关键论文索引</span></div>
           <div><b>47p</b><span>K3 技术报告</span></div>
         </div>
       </aside>
@@ -118,6 +120,22 @@ const paths = [
 
   <section class="section compact release-section" id="new-chapters">
     <div class="release-grid">
+      <a class="release-card multimodal-release" href="/multimodal/">
+        <div>
+          <p class="eyebrow"><span>NEW / CHAPTER 13</span> PIXELS · TOKENS · NATIVE MULTIMODALITY</p>
+          <h2>原生多模态不等于移除视觉塔：真正改变的是数据、目标、优化与行为闭环</h2>
+          <p>
+            用语义空间、连接器、分辨率、OCR、视频、训练、幻觉、评测与 Agent 十六张账，
+            从 ViT、CLIP 和 LLaVA 走到 DeepSeek-VL / Janus / OCR 三分支，以及 Kimi 三代 MoonViT 与 K3 从头共同 NTP。
+          </p>
+        </div>
+        <dl>
+          <div><dt>LINEAGE</dt><dd>2012 → 2026</dd></div>
+          <div><dt>NODES</dt><dd>55 个一手节点</dd></div>
+          <div><dt>LAB</dt><dd>Token · 连接器 · 光学压缩 · 视觉闭环</dd></div>
+        </dl>
+        <span class="release-arrow" aria-hidden="true">从像素进入可验证视觉行动 →</span>
+      </a>
       <a class="release-card agent-release" href="/agents/">
         <div>
           <p class="eyebrow"><span>NEW / CHAPTER 12</span> AGENTS · TOOL USE · ENVIRONMENTS</p>

src/pages/progress/index.astro

@@ -18,6 +18,7 @@ const workstreams = [
   { label: "指令微调与人类偏好", value: 75, next: "加入真实偏好分歧样本、RM 长度偏置与 PPO/DPO 小模型复现" },
   { label: "推理与测试时扩展", value: 76, next: "真实模型采样曲线、PRM 案例与逐篇图表精读" },
   { label: "工具使用与长程 Agent", value: 74, next: "补真实环境 traces、cross-harness 对照、Agent RL 训练曲线与安全案例" },
+  { label: "原生多模态", value: 76, next: "补真实视觉 Token traces、跨分辨率消融、OCR 失败案例与视觉 Agent 安全轨迹" },
   { label: "稀疏计算与 MoE", value: 74, next: "补充真实集群 traces 与专家特化案例" },
   { label: "长上下文专题", value: 72, next: "加入更多论文逐图笔记与真实模型配置对比" },
   { label: "大规模训练系统", value: 71, next: "补真实集群 traces、故障案例与精确 topology 配置" },
@@ -46,7 +47,7 @@ const workstreams = [
         <div><dt>OVERALL</dt><dd>专题平均 {average}%</dd></div>
         <div><dt>READABLE</dt><dd>{published} 个首版可读专题</dd></div>
         <div><dt>ACTIVE</dt><dd>{researching} 个研究/写作中</dd></div>
-        <div><dt>UPDATED</dt><dd>2026-07-29 06:56 CST</dd></div>
+        <div><dt>UPDATED</dt><dd>2026-07-29 07:46 CST</dd></div>
         <div><dt>MODE</dt><dd>持续迭代，不锁死版本</dd></div>
       </dl>
     </div>
@@ -56,7 +57,7 @@ const workstreams = [
     <div class="section-heading">
       <div>
         <p class="eyebrow"><span>01</span> WORKSTREAMS</p>
-        <h2>十七条工作流同时推进，但不混淆“有页面”和“已核验”</h2>
+        <h2>十八条工作流同时推进，但不混淆“有页面”和“已核验”</h2>
       </div>
       <p class="section-lead">
         内容首版优先打通全局脉络；随后每轮迭代选择一个专题推进到论文/工程层，并做独立事实复核。
@@ -93,8 +94,8 @@ const workstreams = [
       <article><span>✓</span><h3>K3 报告已结构化拆解</h3><p>47 页报告目录、151 条参考来源和架构/后训练/系统主线已经提取。</p></article>
       <article><span>✓</span><h3>16 专题知识图</h3><p>从语言模型基础到评测安全，包含先修依赖和三条贯穿案例。</p></article>
       <article><span>✓</span><h3>编辑式网站系统</h3><p>响应式导航、章节模板、侧栏、进度、论文链和证据提示组件。</p></article>
-      <article><span>✓</span><h3>三十九个原创交互视图</h3><p>K3、语言模型前史、Transformer、DeepSeek、长上下文、MoE、推理、Agent，以及训练系统、Scaling、数据工程、数值和 Alignment 专题。</p></article>
-      <article><span>✓</span><h3>十三篇首版长文</h3><p>K3、语言模型前史、Transformer、DeepSeek、Scaling、数据工程、长上下文、MoE、后训练、推理、Agent、训练系统与数值优化专题。</p></article>
+      <article><span>✓</span><h3>四十三个原创交互视图</h3><p>K3、语言模型前史、Transformer、DeepSeek、长上下文、MoE、推理、Agent、多模态，以及训练系统、Scaling、数据工程、数值和 Alignment 专题。</p></article>
+      <article><span>✓</span><h3>十四篇首版长文</h3><p>K3、语言模型前史、Transformer、DeepSeek、Scaling、数据工程、长上下文、MoE、后训练、推理、Agent、原生多模态、训练系统与数值优化专题。</p></article>
       <article><span>✓</span><h3>语言模型前史深度专题</h3><p>八张独立问题账、33 个正式节点、20 段长文与概率—向量—记忆—对齐四联实验。</p></article>
       <article><span>✓</span><h3>Transformer 深度专题</h3><p>十张独立问题账、40 个正式节点、21 段正文与 QKV—Mask—多头位置—Block 成本四联实验。</p></article>
       <article><span>✓</span><h3>Scaling Laws 深度专题</h3><p>九张账、29 个一手节点、DeepSeek/Kimi 双谱系与曲面—部署—复用—涌现四联实验。</p></article>
@@ -106,7 +107,8 @@ const workstreams = [
       <article><span>✓</span><h3>数值、优化器与稳定性深度专题</h3><p>十张账、36 个一手节点、K2/K3 与 DeepSeek-V3/V4 双谱系，以及格式—状态—更新—失稳四联实验。</p></article>
       <article><span>✓</span><h3>指令微调与人类偏好深度专题</h3><p>十二张账、44 个一手节点、DeepSeek/Kimi 后训练双谱系，以及 SFT—RM—PPO/DPO—配方四联实验。</p></article>
       <article><span>✓</span><h3>工具使用与长程 Agent 深度专题</h3><p>十四张账、52 个一手节点、DeepSeek/Kimi Agent 双谱系，以及循环—工具契约—可靠性—长程 RL 四联实验。</p></article>
-      <article><span>✓</span><h3>314 篇关键论文索引</h3><p>新增 TextWorld、WebArena、ToolSandbox、AgentDojo、RAGEN、Agent Lightning、AgentENV 等 34 个 Agent 节点。</p></article>
+      <article><span>✓</span><h3>原生多模态深度专题</h3><p>十六张账、55 个一手节点、DeepSeek 三分支、Kimi 三代 MoonViT，以及 Token—连接器—光学压缩—视觉闭环四联实验。</p></article>
+      <article><span>✓</span><h3>355 篇关键论文索引</h3><p>新增 ResNet、ALIGN、NaViT、DeepSeek-VL2、Janus、DeepSeek-OCR、Vision-R1 等 41 个多模态节点。</p></article>
       <article><span>✓</span><h3>公开仓库与自托管发布</h3><p>源码公开到 git.k1412.top，网站由不可变镜像、Compose Manager 与 HTTPS 交付。</p></article>
     </div>
   </section>
@@ -132,7 +134,7 @@ const workstreams = [
       <div><span>P1</span><strong>推理二轮深化</strong><p>真实 pass@k 曲线 → PRM 失败案例 → 逐篇图表精读</p><em>案例库 + 真实 traces</em></div>
       <div><span>P1</span><strong>Alignment 二轮深化</strong><p>真实偏好分歧 → RM 长度偏置 → PPO/DPO 小模型复现</p><em>数据案例 + 可复现实验</em></div>
       <div><span>P1</span><strong>Agent 二轮深化</strong><p>真实环境 traces → cross-harness ablation → Agent RL 曲线与提示注入案例</p><em>运行证据 + 安全案例库</em></div>
-      <div><span>P2</span><strong>原生多模态</strong><p>ViT/CLIP → connector VLM → Kimi-VL/MoonViT-V2</p><em>视觉 Token 流程图</em></div>
+      <div><span>P1</span><strong>原生多模态二轮</strong><p>真实视觉 Token traces → 跨分辨率 / connector 消融 → OCR 与视觉 Agent 安全失败案例</p><em>运行证据 + 逐图笔记</em></div>
     </div>
   </section>
 
@@ -184,6 +186,9 @@ const workstreams = [
       <div><time>2026-07-29</time><b>Attention 权重与因果解释永久分离</b><p>热力图可描述中间权重和提出假设；因果结论必须补消融、patching 或反事实干预。</p></div>
       <div><time>2026-07-29</time><b>Agent 按十四张账组织</b><p>模型、harness、工具契约、环境、评测器、可靠性与安全不再被压成一个 Agent 分数。</p></div>
       <div><time>2026-07-29</time><b>Agent 完成必须回到 final state</b><p>function schema、工具执行、业务状态、策略合规与 pass^k 分层评价；模型自报完成不作为证据。</p></div>
+      <div><time>2026-07-29</time><b>原生多模态按五层管道与十六张账组织</b><p>像素、视觉塔、压缩 / connector、主干与输出 / 工具闭环分开定位；“原生”再拆成数据、目标、优化、输入输出与 Agent 五维。</p></div>
+      <div><time>2026-07-29</time><b>DeepSeek 多模态永久保留三分支</b><p>VL/VL2 的理解、Janus 的统一生成、OCR 的光学压缩不画成错误的单向代际谱系。</p></div>
+      <div><time>2026-07-29</time><b>光学压缩实验分开报告值、教学插值与证据外区域</b><p>DeepSeek-OCR 的 &lt;10× / 20× 锚点标成作者报告；中间只做显式教学插值，超过范围不外推。</p></div>
     </div>
   </section>