update

build/bib-list.js

@@ -1978,7 +1978,7 @@ var bibtexify = (function($) {
         // adds links to the PDF or url of the item
         links: function(entryData) {
             var itemStr = '';
-            if (entryData.url && (entryData.url.match(/.*\.pdf/)  || entryData.url.match(/\/pdf\//))  ) {
+            if (entryData.url && ( entryData.url.match(/.*\.pdf/)  || entryData.url.match(/\/pdf\//) || entryData.url.match(/pdf\?id=/))  ) {
             itemStr += '&nbsp;<span style="color:white;font-size:12px;background-color:#FFCECE;cursor: pointer;"> <a title="PDF of this paper" href="'+  entryData.url +'" target="_blank"><font color="black">pdf<\/font><\/a>&nbsp;<\/span>';
           //  itemStr += '<button type="button" class="btn btn-danger btn-xs disabled" style="border: none;cursor: pointer;font-size:12px;background-color: #900"> <a title="PDF of this article" href="' +
           //            entryData.url + '" target="_blank"><font color="white">.pdf (draft)<\/font><\/a><\/button>';

references.bib

@@ -41,12 +41,12 @@ @inproceedings{braun2024cake
       year={2024},
       Keywords={Deep Learning, model-agnostic transfer, Knowledge distillation, Student-Teacher},
       Anote={./images/braun2024cake.png},
-			Key = {Student Paper Highlight at AISTATS 2024},
+			Key = {Outstanding Student Paper Highlight at AISTATS 2024},
       Note={Access to pre-trained models has recently emerged as a standard across numerous machine learning domains. Unfortunately, access to the original data the models were trained on may not equally be granted. This makes it tremendously challenging to fine-tune, compress models, adapt continually, or to do any other type of data-driven update. We posit that original data access may however not be required. Specifically, we propose Contrastive Abductive Knowledge Extraction (CAKE), a model-agnostic knowledge distillation procedure that mimics deep classifiers without access to the original data. To this end, CAKE generates pairs of noisy synthetic samples and diffuses them contrastively toward a model’s decision boundary. We empirically corroborate CAKE's effectiveness using several benchmark datasets and various architectural choices, paving the way for broad application.},
       Url={https://proceedings.mlr.press/v238/braun24b/braun24b.pdf}
 }
 
- 
+
 @inproceedings{wuest2024pix2code,
 	Anote={./images/wuest_pix2code.png},
 	title={Pix2Code: Learning to Compose Neural Visual Concepts as Programs},