Publish WIA technical report as a static paper Space

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+cover.png filter=lfs diff=lfs merge=lfs -text
+Tech_Report__WAM.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,33 @@
 ---
 title: WIA Technical Report
-emoji: 🐨
-colorFrom: purple
+emoji: 📄
+colorFrom: yellow
 colorTo: red
 sdk: static
-pinned: false
+app_file: index.html
+fullWidth: true
+short_description: World Intelligence Agent - technical report and PDF
+tags:
+  - technical-report
+  - preprint
+  - world-model
+  - digital-agents
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# World Intelligence Agent: Unifying World Modeling and Action Learning for Digital Agents
+
+**Darwin Agent Team** | **Technical Report / Preprint**
+
+This static Space is the public reading and download page for the WIA technical report.
+It hosts the original PDF, not model weights or a dataset.
+
+- [Read the PDF](https://huggingface.co/spaces/darwinagent/WIA-Technical-Report/blob/main/Tech_Report__WAM.pdf)
+- [Download the PDF](https://huggingface.co/spaces/darwinagent/WIA-Technical-Report/resolve/main/Tech_Report__WAM.pdf?download=true)
+- [Project page](https://darwin-agent.github.io/WIA/)
+
+WIA unifies world modeling and action learning for digital agents. The report introduces
+WIA-Corpus and WIA-Bench, presents the WIA-WM family of world models, and explores
+simulation-based training, inference lookahead, and WIA-WAM for action generation.
+
+Please refer to the full report for methods, experimental protocols, results, limitations,
+and the complete contributor list.

Tech_Report__WAM.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e437dba9d47357cb44e626d6405399442ddf723785c163d426ec64ac167ff4d8
+size 13512794

index.html

@@ -1,19 +1,190 @@
 <!doctype html>
-<html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="World Intelligence Agent: Unifying World Modeling and Action Learning for Digital Agents. Read and download the Darwin Agent Team technical report.">
+    <meta property="og:title" content="World Intelligence Agent | Technical Report">
+    <meta property="og:description" content="Unifying World Modeling and Action Learning for Digital Agents. A technical report by the Darwin Agent Team.">
+    <meta property="og:type" content="website">
+    <meta property="og:image" content="https://huggingface.co/spaces/darwinagent/WIA-Technical-Report/resolve/main/cover.png">
+    <title>World Intelligence Agent | Technical Report</title>
+    <style>
+      :root {
+        color-scheme: light;
+        --ink: #202b2e;
+        --muted: #607074;
+        --accent: #d64716;
+        --line: #e3e7e3;
+        --paper: #ffffff;
+        --canvas: #f7f8f4;
+      }
+
+      * { box-sizing: border-box; }
+
+      body {
+        margin: 0;
+        background: var(--canvas);
+        color: var(--ink);
+        font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Arial, sans-serif;
+        -webkit-font-smoothing: antialiased;
+      }
+
+      a { color: inherit; }
+      a:focus-visible { outline: 3px solid var(--accent); outline-offset: 5px; }
+
+      .shell { width: min(1120px, calc(100% - 64px)); margin: 0 auto; }
+
+      header {
+        display: flex;
+        align-items: center;
+        justify-content: space-between;
+        gap: 24px;
+        padding: 28px 0;
+        border-bottom: 1px solid var(--line);
+      }
+
+      .brand { font-size: 17px; font-weight: 750; letter-spacing: -.4px; }
+      .brand span { color: var(--accent); }
+      .header-link { color: var(--muted); font-size: 14px; text-decoration: none; }
+      .header-link:hover { color: var(--accent); }
+
+      .hero {
+        display: grid;
+        grid-template-columns: minmax(0, 1fr) 330px;
+        align-items: start;
+        gap: 64px;
+        padding: 60px 0 48px;
+      }
+
+      .eyebrow {
+        display: inline-block;
+        margin: 0 0 24px;
+        color: var(--accent);
+        font-size: 12px;
+        font-weight: 750;
+        letter-spacing: 1.6px;
+        text-transform: uppercase;
+      }
+
+      h1 { margin: 0; font-size: clamp(38px, 4.6vw, 58px); line-height: 1.08; letter-spacing: -2px; }
+      .subtitle { margin: 20px 0 0; font-size: 26px; line-height: 1.36; letter-spacing: -.5px; }
+      .authors { margin: 25px 0 0; color: var(--muted); font-size: 16px; }
+      .intro { margin: 28px 0 0; max-width: 580px; color: var(--muted); font-size: 17px; line-height: 1.75; }
+
+      .actions { display: flex; flex-wrap: wrap; gap: 12px; margin-top: 30px; }
+
+      .button {
+        display: inline-flex;
+        align-items: center;
+        justify-content: center;
+        min-height: 48px;
+        padding: 12px 20px;
+        border: 1px solid var(--line);
+        border-radius: 8px;
+        background: var(--paper);
+        font-size: 14px;
+        font-weight: 650;
+        text-decoration: none;
+      }
+
+      .button:hover { border-color: var(--accent); }
+      .button.primary { border-color: var(--accent); background: var(--accent); color: #fff; }
+      .button.primary:hover { background: #b9360c; }
+      .file-note { margin: 15px 0 0; color: var(--muted); font-size: 12px; }
+
+      figure { margin: 0; }
+      .cover-link { display: block; padding: 12px; border: 1px solid var(--line); border-radius: 12px; background: var(--paper); box-shadow: 0 18px 36px #25372c0c; }
+      .cover { display: block; width: 100%; height: auto; }
+      figcaption { margin-top: 16px; color: var(--muted); font-size: 12px; text-align: center; }
+
+      .overview { padding: 38px 0 48px; border-top: 1px solid var(--line); }
+      h2 { margin: 0 0 18px; font-size: 24px; letter-spacing: -.5px; }
+      .overview > p { max-width: 960px; margin: 0; color: var(--muted); font-size: 16px; line-height: 1.85; }
+      .topics { display: grid; grid-template-columns: repeat(3, minmax(0, 1fr)); gap: 18px; margin-top: 30px; }
+      .topic { padding: 23px; border: 1px solid var(--line); border-radius: 10px; background: var(--paper); }
+      h3 { margin: 0 0 10px; font-size: 16px; }
+      .topic p { margin: 0; color: var(--muted); font-size: 14px; line-height: 1.7; }
+
+      footer { padding: 25px 0 30px; border-top: 1px solid var(--line); color: var(--muted); font-size: 12px; line-height: 1.7; }
+      footer p { margin: 0; }
+
+      @media (max-width: 900px) {
+        .hero { grid-template-columns: minmax(0, 1fr) 260px; gap: 32px; }
+        .subtitle { font-size: 23px; }
+      }
+
+      @media (max-width: 700px) {
+        .shell { width: min(560px, calc(100% - 36px)); }
+        header { padding: 22px 0; }
+        .hero { grid-template-columns: minmax(0, 1fr); gap: 36px; padding-top: 38px; }
+        h1 { font-size: 42px; letter-spacing: -1.5px; }
+        .subtitle { font-size: 23px; }
+        figure { width: min(330px, 100%); margin: 0 auto; }
+        .topics { grid-template-columns: minmax(0, 1fr); }
+        .overview { padding-top: 30px; }
+      }
+
+      @media (max-width: 360px) {
+        h1 { font-size: 36px; }
+        .header-link { font-size: 12px; }
+      }
+    </style>
+  </head>
+  <body>
+    <div class="shell">
+      <header>
+        <div class="brand">Darwin <span>Agent</span></div>
+        <a class="header-link" href="https://darwin-agent.github.io/WIA/" target="_blank" rel="noopener noreferrer">Project website ↗</a>
+      </header>
+
+      <main>
+        <section class="hero" aria-labelledby="report-title">
+          <div>
+            <p class="eyebrow">Technical Report / Preprint</p>
+            <h1 id="report-title">World Intelligence Agent</h1>
+            <p class="subtitle">Unifying World Modeling and Action Learning for Digital Agents</p>
+            <p class="authors">Darwin Agent Team</p>
+            <p class="intro">A unified approach to understanding how actions change the world and learning how digital agents should act.</p>
+            <div class="actions">
+              <a class="button primary" href="https://huggingface.co/spaces/darwinagent/WIA-Technical-Report/blob/main/Tech_Report__WAM.pdf" target="_blank" rel="noopener noreferrer">Read the paper ↗</a>
+              <a class="button" href="https://huggingface.co/spaces/darwinagent/WIA-Technical-Report/resolve/main/Tech_Report__WAM.pdf?download=true">Download PDF ↓</a>
+            </div>
+            <p class="file-note">70 pages · PDF · 12.9 MiB · Original report</p>
+          </div>
+
+          <figure>
+            <a class="cover-link" href="https://huggingface.co/spaces/darwinagent/WIA-Technical-Report/blob/main/Tech_Report__WAM.pdf" target="_blank" rel="noopener noreferrer" aria-label="Read the full World Intelligence Agent technical report">
+              <img class="cover" src="cover.png" width="1159" height="1500" alt="First page of the World Intelligence Agent report, showing its title, abstract, and evaluation overview.">
+            </a>
+            <figcaption>Preview of the report's first page</figcaption>
+          </figure>
+        </section>
+
+        <section class="overview" aria-labelledby="overview-title">
+          <h2 id="overview-title">About this report</h2>
+          <p>World Intelligence Agent (WIA) brings together world modeling and action learning for digital agents. The report introduces WIA-Corpus and WIA-Bench, presents the WIA-WM family of world models, and explores simulation-based training and inference lookahead. It then extends the world-model interface toward action generation with WIA-WAM.</p>
+          <div class="topics">
+            <article class="topic">
+              <h3>World modeling</h3>
+              <p>Predicting the observations induced by actions, connecting perception, planning, and policy learning.</p>
+            </article>
+            <article class="topic">
+              <h3>Data and evaluation</h3>
+              <p>WIA-Corpus and WIA-Bench support training and evaluation across seven digital domains.</p>
+            </article>
+            <article class="topic">
+              <h3>Action learning</h3>
+              <p>Simulation-based learning and the WIA-WAM extension connect world models to policy decision-making.</p>
+            </article>
+          </div>
+        </section>
+      </main>
+
+      <footer>
+        <p>Darwin Agent Team · Technical Report / Preprint</p>
+        <p>See the full report for methods, experimental protocols, results, limitations, and the complete contributor list.</p>
+      </footer>
+    </div>
+  </body>
 </html>