Updated on 2024-12-31

Author: lxaw

papers/list.json

@@ -1,4 +1,13 @@
 [
+  {
+    "title": "Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention",
+    "author": "Angelos Katharopoulos et al",
+    "year": "2020",
+    "topic": "attention, transformer",
+    "venue": "ICML",
+    "description": "This paper rephrases transformers as RNNs (title). They express the self-attention mechanism as a linear dot-product of kernel feature maps to make the complexity go from O(N^2) to O(N). Personal note: this is the 200th paper recorded on here, and the last of 2024! Summer of 2024 was when I began studying machine learning. Let's keep it up!",
+    "link": "https://arxiv.org/pdf/2006.16236"
+  },
   {
     "title": "Prefix-Tuning: Optimizing Continuous Prompts for Generation",
     "author": "Xiang Lisa Li et al",

papers_read.html

@@ -16,10 +16,10 @@ <h1>Here's where I keep a list of papers I have read.</h1>
         I typically use this to organize papers I found interesting. Please feel free to do whatever you want with it. Note that this is not every single paper I have ever read, just a collection of ones that I remember to put down.
     </p>
     <p id="paperCount">
-        So far, we have read 199 papers. Let's keep it up!
+        So far, we have read 200 papers. Let's keep it up!
     </p> 
     <small id="searchCount">
-        Your search returned 199 papers. Nice! 
+        Your search returned 200 papers. Nice! 
     </small>
 
     <div class="search-inputs">
@@ -46,6 +46,16 @@ <h1>Here's where I keep a list of papers I have read.</h1>
         </thead>
         <tbody>
 
+            <tr>
+                <td>Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention</td>
+                <td>Angelos Katharopoulos et al</td>
+                <td>2020</td>
+                <td>attention, transformer</td>
+                <td>ICML</td>
+                <td>This paper rephrases transformers as RNNs (title). They express the self-attention mechanism as a linear dot-product of kernel feature maps to make the complexity go from O(N^2) to O(N). Personal note: this is the 200th paper recorded on here, and the last of 2024! Summer of 2024 was when I began studying machine learning. Let&#x27;s keep it up!</td>
+                <td><a href="https://arxiv.org/pdf/2006.16236" target="_blank">Link</a></td>
+            </tr>
+        
             <tr>
                 <td>Prefix-Tuning: Optimizing Continuous Prompts for Generation</td>
                 <td>Xiang Lisa Li et al</td>