1.0Alignment for Vision-Language Foundation Models https://mscvprojects.ri.cmu.edu/2024team8RELATED WORK - Alignment for Vision-Language Foundation Modelsrich600338<blockquote class="wp-embedded-content" data-secret="jtaW6mrUcP"><a href="https://mscvprojects.ri.cmu.edu/2024team8/related-work/">RELATED WORK</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://mscvprojects.ri.cmu.edu/2024team8/related-work/embed/#?secret=jtaW6mrUcP" width="600" height="338" title="“RELATED WORK” — Alignment for Vision-Language Foundation Models " data-secret="jtaW6mrUcP" 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>
· A pioneer text-to-image benchmark Involving human preferences · Limitations: excessive noise and lack of compositional information 2. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation · Rich compositional information considered for text-to-image generation. · VQA formula employed for text-to-visual evaluation, yet lacks generalization. 3. When and Why Vision-Language Models Behave Like Bags-Of-Words, and What to … Continue reading ""https://lh7-us.googleusercontent.com/HEMasLyCaEGcbOheYYpEABgvvk5CWdA1KuJ-xeSbQGhAzDSLYpruwN16H6EbhQ4ktK5MhY4a7J7sy1d1FNT08RnDUB_5Jg7mLjQWDiJ7kEH8gSoq4gb6G8ov010H6Lecq0_fkyyUGVDHiPhZRV7Voi5L1w=s2048