1.0Alignment for Vision-Language Foundation Models https://mscvprojects.ri.cmu.edu/2024team8About - Alignment for Vision-Language Foundation Modelsrich600338<blockquote class="wp-embedded-content" data-secret="j0iigPCbBY"><a href="https://mscvprojects.ri.cmu.edu/2024team8/">About</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://mscvprojects.ri.cmu.edu/2024team8/embed/#?secret=j0iigPCbBY" width="600" height="338" title="“About” — Alignment for Vision-Language Foundation Models " data-secret="j0iigPCbBY" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script>
/*! This file is auto-generated */
!function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document);
//# sourceURL=https://mscvprojects.ri.cmu.edu/2024team8/wp-includes/js/wp-embed.min.js
</script>
Text-to-visual models, which now create realistic images and videos, face challenges with complex prompts involving attributes, relationships, and advanced reasoning. Our study on GenAI-Bench evaluates top image and video generators for these tasks. We compare automated evaluation metrics against our collected human ratings and find that VQAScore significantly outperforms previous metrics such as CLIPScore. In … Continue reading ""https://mscvprojectsricmu.files.wordpress.com/2024/05/1715380758753.png?w=1024