camera ready updates

claws-lab · Jul 21, 2024 · b23b318 · b23b318
1 parent 447cd73
commit b23b318
Show file tree

Hide file tree

Showing 5 changed files with 13 additions and 14 deletions.
diff --git a/README.md b/README.md
@@ -1,5 +1,5 @@
 
-# Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities *Without* Richer Cross-Modal Projections   
+# Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space   
 *Paper*: [https://arxiv.org/abs/2402.16832](https://arxiv.org/abs/2402.16832)  
 *Webpage*: [https://claws-lab.github.io/projection-in-MLLMs/](https://claws-lab.github.io/projection-in-MLLMs/)  
 *GitHub*: [https://github.com/claws-lab/projection-in-MLLMs](https://github.com/claws-lab/projection-in-MLLMs/)   
@@ -67,10 +67,10 @@ The code for the experiments is available in the `experiments` directory. The `e
 ### Citation
 If you use this codebase, please cite our paper:
 ```bibtex
-@article{verma2024mysterious,
-  title={Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities Without Richer Cross-Modal Projections},
+@article{verma2024crossmodalprojection,
+  title={Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space},
   author={Verma, Gaurav and Choi, Minje and Sharma, Kartik and Watson-Daniels, Jamelle and Oh, Sejoon and Kumar, Srijan},
-  journal={arXiv preprint arXiv:2402.16832},
+  journal={62nd Annual Meeting of the Association for Computational Linguistics (ACL)},
   year={2024}
 }
 ```

diff --git a/assets/acl-logo.png b/assets/acl-logo.png
diff --git a/assets/projection-in-MLLMs.pdf b/assets/projection-in-MLLMs.pdf
diff --git a/assets/screenshot.png b/assets/screenshot.png
diff --git a/index.html b/index.html
@@ -153,19 +153,18 @@
 <head>
 	<title>MLLM Projections</title>
 	<meta property="og:image" content="./assets/teaser.png"/> 
-	<meta property="og:title" content="Cross-modal Projection in Multimodal LLMs" />
-	<meta property="og:description" content="Paper title: Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities Without Richer Cross-Modal Projections; Authors: Gaurav Verma, Minje Choi, Kartik Sharma, Jamelle Watson-Daniels, Sejoon Oh, Srijan Kumar; Affiliations: Georgia Institute of Technology" />
+	<meta property="og:title" content="Cross-Modal Projection in Multimodal LLMs" />
+	<meta property="og:description" content="Paper Title: Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space (ACL 2024 Main); Authors: Gaurav Verma, Minje Choi, Kartik Sharma, Jamelle Watson-Daniels, Sejoon Oh, Srijan Kumar; Affiliations: Georgia Institute of Technology" />
 
-	<!-- Get from Google Analytics -->
-	<!-- Global site tag (gtag.js) - Google Analytics -->
 	<script async src=""></script> 
 </head>
 
 <body>
 	<br>
 	<center>
-		<span style="font-size:36px">Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities <em>Without</em> Richer Cross-Modal Projections</span><br/>
+		<span style="font-size:36px">Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space</span><br/>
 		<span style="font-size:25px">[<a href="https://arxiv.org/abs/2402.16832">Paper</a>] &nbsp;&nbsp; [<a href="https://github.com/claws-lab/projection-in-MLLMs">GitHub</a>]</span><br/><br/>
+		<span><img src ="assets/acl-logo.png" width="250px;"/></span><br/><br/>
 		<span><a href="https://gaurav22verma.github.io/">Gaurav Verma</a><sup>1</sup>, 
 			<a href="https://minjechoi.github.io/">Minje Choi</a><sup>1</sup>, 
 			<a href="https://ksartik.github.io/">Kartik Sharma</a><sup>1</sup>,<br/>
@@ -242,9 +241,9 @@
 		<tr>
 			<td><a href="./assets/projection-in-MLLMs.pdf"><img class="layered-paper-big" style="height:175px" src="./assets/screenshot.png"/></a></td>
 			<td>
-				<span style="font-size:12pt">Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities Without Richer Cross-Modal Projections<br>
+				<span style="font-size:12pt">Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space<br>
 				Gaurav Verma, Minje Choi, Kartik Sharma, Jamelle Watson-Daniels, Sejoon Oh, Srijan Kumar<br>
-				arXiv preprint 2402.NNNNN<br><br/>
+				62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)<br/>
 				Webpage: <a href="https://claws-lab.github.io/projection-in-MLLMs">https://claws-lab.github.io/projection-in-MLLMs</a><br/>
 				Code: <a href="https://github.com/claws-lab/projection-in-MLLMs">https://github.com/claws-lab/projection-in-MLLMs</a><br/>
 				arXiv: <a href="https://arxiv.org/abs/2402.16832">https://arxiv.org/abs/2402.16832</a></span><br><br/><br/>
@@ -258,10 +257,10 @@
 				<span style="font-size: 14pt">Bibtex:</span><br/><br/>
 				<left>
 				<code>
-					@article{verma2024mysterious,<br/>
-						title={Mysterious Projections: Multimodal LLMs Gain Domain-Specific Visual Capabilities Without Richer Cross-Modal Projections},<br/>
+					@article{verma2024crossmodalprojection,<br/>
+						title={Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space},<br/>
 						author={Verma, Gaurav and Choi, Minje and Sharma, Kartik and Watson-Daniels, Jamelle and Oh, Sejoon and Kumar, Srijan},<br/>
-						journal={arXiv preprint arXiv:2402.16832},<br/>
+						journal={62nd Annual Meeting of the Association for Computational Linguistics (ACL)},<br/>
 						year={2024}<br/>
 					}
 				</code>