Spaces:

metacritical
/

DeepSeekPapers

Running

App Files Files Community

metacritical commited on 20 days ago

Commit

2ca9a47

verified ·

1 Parent(s): 1cb8f7f

Updated

Browse files

Updated.

Files changed (1) hide show

index.html +258 -20

index.html CHANGED Viewed

@@ -2,24 +2,18 @@
 <html>
 <head>
   <meta charset="utf-8">
-  <meta name="description"
-        content="A collection of research papers from DeepSeek.">
   <meta name="keywords" content="DeepSeek, AI Research, Machine Learning">
   <meta name="viewport" content="width=device-width, initial-scale=1">
   <title>DeepSeek Research Papers</title>
-  <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
-        rel="stylesheet">
   <link rel="stylesheet" href="./static/css/bulma.min.css">
   <link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
   <link rel="stylesheet" href="./static/css/bulma-slider.min.css">
   <link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
-  <link rel="stylesheet"
-        href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
   <link rel="stylesheet" href="./static/css/index.css">
   <link rel="icon" href="./static/images/favicon.svg">
   <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
   <script defer src="./static/js/fontawesome.all.min.js"></script>
   <script src="./static/js/bulma-carousel.min.js"></script>
@@ -27,7 +21,6 @@
   <script src="./static/js/index.js"></script>
 </head>
 <body>
 <section class="hero">
   <div class="hero-body">
     <div class="container is-max-desktop">
@@ -42,7 +35,6 @@
     </div>
   </div>
 </section>
 <section class="hero teaser">
   <div class="container is-max-desktop">
     <div class="hero-body">
@@ -52,7 +44,6 @@
     </div>
   </div>
 </section>
 <section class="section">
   <div class="container is-max-desktop">
     <div class="columns is-centered">
@@ -78,7 +69,6 @@
               <span class="is-size-6 has-text-grey">{Jan 6, 2024}</span>
             </div>
           </div>
           <!-- Paper 2 -->
           <div class="paper-item box">
             <h3 class="title is-4">2. DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models</h3>
@@ -96,18 +86,267 @@
               <span class="is-size-6 has-text-grey">{Jan 11, 2024}</span>
             </div>
           </div>
-          <!-- Remaining papers follow the same structure -->
-          <!-- Paper 3 to 17 would be added here with the same pattern -->
         </div>
         <!-- Paper List End -->
       </div>
     </div>
   </div>
 </section>
 <footer class="footer">
   <div class="container">
     <div class="content has-text-centered">
@@ -120,6 +359,5 @@
     </div>
   </div>
 </footer>
 </body>
 </html>

 <html>
 <head>
   <meta charset="utf-8">
+  <meta name="description" content="A collection of research papers from DeepSeek.">
   <meta name="keywords" content="DeepSeek, AI Research, Machine Learning">
   <meta name="viewport" content="width=device-width, initial-scale=1">
   <title>DeepSeek Research Papers</title>
+  <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
   <link rel="stylesheet" href="./static/css/bulma.min.css">
   <link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
   <link rel="stylesheet" href="./static/css/bulma-slider.min.css">
   <link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
+  <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
   <link rel="stylesheet" href="./static/css/index.css">
   <link rel="icon" href="./static/images/favicon.svg">
   <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
   <script defer src="./static/js/fontawesome.all.min.js"></script>
   <script src="./static/js/bulma-carousel.min.js"></script>
   <script src="./static/js/index.js"></script>
 </head>
 <body>
 <section class="hero">
   <div class="hero-body">
     <div class="container is-max-desktop">
     </div>
   </div>
 </section>
 <section class="hero teaser">
   <div class="container is-max-desktop">
     <div class="hero-body">
     </div>
   </div>
 </section>
 <section class="section">
   <div class="container is-max-desktop">
     <div class="columns is-centered">
               <span class="is-size-6 has-text-grey">{Jan 6, 2024}</span>
             </div>
           </div>
           <!-- Paper 2 -->
           <div class="paper-item box">
             <h3 class="title is-4">2. DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models</h3>
               <span class="is-size-6 has-text-grey">{Jan 11, 2024}</span>
             </div>
           </div>
+          <!-- Paper 3 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">3. DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence</h3>
+            <p>Investigating the intersection of large language models and programming.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2401.14196" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Jan 25, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 4 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">4. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models</h3>
+            <p>Advancing mathematical reasoning capabilities in open language models.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2402.03300" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Feb 6, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 5 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">5. DeepSeek-VL: Towards Real-World Vision-Language Understanding</h3>
+            <p>Focusing on real-world vision-language understanding.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2403.05525" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Mar 9, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 6 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">6. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model</h3>
+            <p>Developing a strong, economical, and efficient Mixture-of-Experts language model.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2405.04434" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{May 7, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 7 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">7. DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data</h3>
+            <p>Using large-scale synthetic data to advance theorem proving in LLMs.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2405.14333" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{May 23, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 8 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">8. DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence</h3>
+            <p>Aiming to surpass closed-source models in code intelligence.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2406.11931" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Jun 17, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 9 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">9. Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models</h3>
+            <p>Fine-tuning sparse architectural large language models with expert specialization.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2407.01906" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Jul 2, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 10 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">10. DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search</h3>
+            <p>Utilizing proof assistant feedback for reinforcement learning and Monte-Carlo Tree Search.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2408.08152" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Aug 15, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 11 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">11. Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation</h3>
+            <p>Decoupling visual encoding for unified multimodal understanding and generation.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2410.13848" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Oct 17, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 12 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">12. JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation</h3>
+            <p>Harmonizing autoregression and rectified flow for unified multimodal understanding and generation.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2411.07975" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Nov 12, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 13 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">13. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding</h3>
+            <p>Mixture-of-Experts Vision-Language Models for advanced multimodal understanding.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2412.10302" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Dec 13, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 14 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">14. DeepSeek-V3 Technical Report</h3>
+            <p>Technical report for DeepSeek-V3.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2412.19437" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Dec 27, 2024}</span>
+            </div>
+          </div>
+          <!-- Paper 15 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">15. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning</h3>
+            <p>Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2501.12948" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Jan 27, 2025}</span>
+            </div>
+          </div>
+          <!-- Paper 16 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">16. Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling</h3>
+            <p>Unified Multimodal Understanding and Generation with Data and Model Scaling.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2501.17811" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Jan 31, 2025}</span>
+            </div>
+          </div>
+          <!-- Paper 17 -->
+          <div class="paper-item box">
+            <h3 class="title is-4">17. Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention</h3>
+            <p>Hardware-Aligned and Natively Trainable Sparse Attention.</p>
+            <div class="publication-links">
+              <span class="link-block">
+                <a href="https://arxiv.org/abs/2502.11089" target="_blank"
+                   class="external-link button is-normal is-rounded is-dark">
+                  <span class="icon">
+                      <i class="fas fa-file-pdf"></i>
+                  </span>
+                  <span>Paper</span>
+                </a>
+              </span>
+              <span class="is-size-6 has-text-grey">{Feb 16, 2025}</span>
+            </div>
+          </div>
         </div>
         <!-- Paper List End -->
       </div>
     </div>
   </div>
 </section>
 <footer class="footer">
   <div class="container">
     <div class="content has-text-centered">
     </div>
   </div>
 </footer>
 </body>
 </html>