Simplify organization card to the requested introduction

README.md

@@ -7,6 +7,4 @@ sdk: static
 pinned: false
 ---
 
-# OpenMLRL
-
-We are a group of researchers working on reinforcement learning for collaborative language model systems. Our work covers multi-agent reinforcement learning, preference learning, multi-turn interaction, and decentralized systems.
+We are a group of researchers working on reinforcement learning for collaborative language model systems. Our work covers multi-agent reinforcement learning, preference learning, multi-turn interaction, and decentralized systems.

index.html

@@ -3,37 +3,10 @@
 <head>
   <meta charset="utf-8">
   <meta name="viewport" content="width=device-width, initial-scale=1">
-  <meta name="description" content="OpenMLRL: open-source frameworks and tools for multi-LLM reinforcement learning.">
-  <title>OpenMLRL — Multi-LLM Reinforcement Learning</title>
+  <title>OpenMLRL</title>
   <link rel="stylesheet" href="style.css">
-  <base target="_blank">
 </head>
 <body>
-  <main>
-    <header>
-      <h1>OpenMLRL</h1>
-      <h3>Multi-LLM Reinforcement Learning</h3>
-      <p>We build open-source frameworks and tools for training language models to work together. Our research explores cooperative reinforcement learning, preference learning, multi-turn interaction, and decentralized multi-agent systems.</p>
-      <p class="links"><a href="https://openmlrl.github.io/">Website</a> · <a href="https://github.com/OpenMLRL">GitHub</a> · <a href="https://openmlrl.github.io/research/">Research</a> · <a href="mailto:liu.shuo2@northeastern.edu">Contact</a></p>
-    </header>
-    <section>
-      <h2>CoMLRL</h2>
-      <p><a href="https://github.com/OpenMLRL/CoMLRL">Cooperative Multi-LLM Reinforcement Learning (CoMLRL)</a> is our library for training teams of language models with multi-agent reinforcement learning. It provides policy-gradient, actor-critic, and preference-based methods, with support for decentralized agents and centralized alternatives.</p>
-      <p class="links"><a href="https://openmlrl.github.io/CoMLRL/">Read the documentation</a> · <a href="https://github.com/OpenMLRL/CoMLRL">Explore the code</a></p>
-    </section>
-    <section>
-      <h2>Environments</h2>
-      <ul>
-        <li><strong><a href="https://github.com/OpenMLRL/LLM_Collab_Writing">Writing</a></strong> — Collaborative summarization and article writing.</li>
-        <li><strong><a href="https://github.com/OpenMLRL/LLM_Collab_Code_Generation">Coding</a></strong> — Cooperative code generation.</li>
-        <li><strong><a href="https://github.com/OpenMLRL/LLM_Collab_Travel">Travel</a></strong> — Travel planning under user constraints.</li>
-        <li><strong><a href="https://github.com/OpenMLRL/LLM_Collab_BFCL">Tool Use</a></strong> — Collaborative function calling with BFCL v4.</li>
-      </ul>
-    </section>
-    <section>
-      <h2>Get involved</h2>
-      <p>Explore our <a href="https://huggingface.co/OpenMLRL/datasets">datasets</a>, read our <a href="https://openmlrl.github.io/research/">research</a>, or contribute through <a href="https://github.com/OpenMLRL">GitHub</a>. For research inquiries, contact <a href="mailto:liu.shuo2@northeastern.edu">liu.shuo2@northeastern.edu</a>.</p>
-    </section>
-  </main>
+  <main><p>We are a group of researchers working on reinforcement learning for collaborative language model systems. Our work covers multi-agent reinforcement learning, preference learning, multi-turn interaction, and decentralized systems.</p></main>
 </body>
 </html>

style.css

@@ -1,17 +1,5 @@
-:root { color-scheme: light dark; --text: #263244; --muted: #596579; --link: #3262a8; --line: #e5e9ef; --background: #ffffff; }
-* { box-sizing: border-box; }
-body { margin: 0; background: var(--background); color: var(--text); font: 15px/1.7 -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; }
-main { max-width: 860px; margin: 0 auto; padding: 28px 32px; }
-h1 { margin: 0 0 2px; font-size: 32px; line-height: 1.25; letter-spacing: -0.7px; }
-h3 { margin: 0 0 16px; font-size: 17px; font-weight: 500; color: var(--muted); }
-h2 { margin: 22px 0 8px; font-size: 20px; line-height: 1.4; }
-p { margin: 9px 0; }
-a { color: var(--link); text-decoration: none; }
-a:hover { text-decoration: underline; }
-a:focus-visible { outline: 2px solid var(--link); outline-offset: 4px; }
-.links { margin-top: 14px; }
-header { padding-bottom: 14px; border-bottom: 1px solid var(--line); }
-ul { margin: 8px 0; padding-left: 22px; }
-li { margin: 4px 0; }
-@media (max-width: 520px) { main { padding: 20px 18px; } h1 { font-size: 28px; } }
-@media (prefers-color-scheme: dark) { :root { --text: #e1e6ee; --muted: #a6b0c1; --link: #99bdf4; --line: #30394a; --background: #111827; } }
+:root { color-scheme: light dark; }
+body { margin: 0; color: #263244; background: #fff; font: 16px/1.7 -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; }
+main { padding: 20px 24px; }
+p { margin: 0; }
+@media (prefers-color-scheme: dark) { body { color: #e1e6ee; background: #111827; } }