<!DOCTYPE html><html lang="en" xmlns="http://www.w3.org/1999/xhtml" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" style="font-size:16px;"><head></head><head><meta charset="utf-8"/><!--[if !mso]><!--><meta http-equiv="X-UA-Compatible" content="IE=edge"/><!--<![endif]--><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="x-apple-disable-message-reformatting"/><meta name="format-detection" content="telephone=no,address=no,email=no,date=no,url=no"/><meta name="color-scheme" content="light"/><meta name="supported-color-schemes" content="light"/><title>Prophesy in LLMs: DIFFUSION LANGUAGE MODELS KNOW THE ANSWER BEFORE DECODING </title><!--[if mso]><xml><o:OfficeDocumentSettings><o:AllowPNG/><o:PixelsPerInch>96</o:PixelsPerInch></o:OfficeDocumentSettings></xml><![endif]--><style>
:root { color-scheme: light; supported-color-schemes: light; }
body { margin: 0; padding: 0; min-width: 100%!important; -ms-text-size-adjust: 100% !important; -webkit-transform: scale(1) !important; -webkit-text-size-adjust: 100% !important; -webkit-font-smoothing: antialiased !important; }
.body { word-wrap: normal; word-spacing:normal; }
table.mso { width: 100%; border-collapse: collapse; padding: 0; table-layout: fixed; }
img { border: 0; outline: none; }
table { mso-table-lspace: 0px; mso-table-rspace: 0px; }
td, a, span { mso-line-height-rule: exactly; }
#root [x-apple-data-detectors=true],
a[x-apple-data-detectors=true],
#MessageViewBody a { color: inherit !important; text-decoration: inherit !important; font-size: inherit !important; font-family: inherit !important; font-weight: inherit !important; line-height: inherit !important; }
span.MsoHyperlink { color: inherit !important; mso-style-priority: 99 !important; }
span.MsoHyperlinkFollowed { color: inherit !important; mso-style-priority: 99 !important; }
.a { background-color:#dedede; }
.b { background-color:#2a2a2a; }
.c { background-color:#ffffff; }
.d { background-color:#fff0c8; }
.d2 { background-color:#FFFFFF; }
.d3 { background-color:#FFFFFF; }
h1 a { text-decoration:none;color:#2C81E5;font-style:italic; }
h2 a { text-decoration:none;color:#2C81E5;font-style:italic; }
h3 a { text-decoration:none;color:#2C81E5;font-style:italic; }
h4 a { text-decoration:none;color:#2C81E5;font-style:italic; }
h5 a { text-decoration:none;color:#2C81E5;font-style:italic; }
h6 a { text-decoration:none;color:#2C81E5;font-style:italic; }
h1, h1 a, h2, h2 a, h3, h3 a, h4, h4 a, h5, h5 a, h6, h6 a, ul, li, ol, p, p a { margin: 0;padding: 0; }
h1 { font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif;font-weight:700;font-size:28px;color:#2A2A2A;line-height:42px;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
h2 { font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif;font-weight:700;font-size:24px;color:#2A2A2A;line-height:36px;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
h3 { font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif;font-weight:400;font-size:20px;color:#2A2A2A;line-height:30px;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
h4 { font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif;font-weight:400;font-size:18px;color:#2A2A2A;line-height:27px;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
h5 { font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif;font-weight:400;font-size:16px;color:#2A2A2A;line-height:24px;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
h6 { font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif;font-weight:400;font-size:14px;color:#2A2A2A;line-height:21px;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
p { font-family:'Georgia','Times New Roman',serif;font-weight:400;color:#2D2D2D;font-size:16px;line-height:24px;padding-bottom:8px;padding-top:8px;mso-margin-top-alt:8px;mso-margin-bottom-alt:8px; }
p a, .e a, ul a, li a, .h a, .h2 a, .h3 a { word-break:break-word;color:#2C81E5 !important;text-decoration:none;font-style:italic; }
p a span, .e a span, ul a span, li a span { color: inherit }
p .bold { font-weight:bold;color:#2D2D2D; }
p span[style*="font-size"] { line-height: 1.6; }
.f p { font-size:12px;line-height:15px;color:#2D2D2D;padding:0; }
.f p a { color:#2D2D2D !important; }
.g p { font-family:'Helvetica',Arial,sans-serif;font-size:14px;line-height:20px;font-weight:normal;margin:0; }
.g p a { text-decoration: underline; }
.i p { font-family:'Helvetica',Arial,sans-serif;line-height:23px;font-size:15px;color:#2D2D2D; }
.i p a { color:#2D2D2D !important; }
.i2 p { font-family:'Helvetica',Arial,sans-serif;line-height:23px;font-size:15px;color:#2D2D2D; }
.i2 p a { color:#2D2D2D !important; }
.i3 p { font-family:'Helvetica',Arial,sans-serif;line-height:43px;font-size:24px;color:#2D2D2D; }
.i3 p a { color:#2D2D2D !important; }
.h p a { color:#595959 !important; }
.h2 p a { color:#595959 !important; }
.h3 p a { color:#595959 !important; }
.f p a, .i p a, .i2 p a, .i3 p a, .h p a, .h2 p a, .h3 p a { text-decoration:underline; }
.j { border-top:3px solid #ffeb2d; }
.k p { padding-left:15px;padding-bottom:0px;padding-top:6px;mso-margin-top-alt:6px;mso-margin-bottom-alt:0px;mso-margin-left-alt:15px; }
.o { background-color:#FFFFFF;border:1px solid #F1F1F1;border-radius:5px; }
.o p { font-family:'Helvetica',Arial,sans-serif;padding:0px;margin:0px; }
.l p,
.l p a, .l a { font-size:14px;line-height:20px;font-weight: bold;color:#2D2D2D;padding-bottom:6px;mso-margin-bottom-alt:6px;text-decoration:none; }
.m p,
.m p a { font-size:13px;line-height:18px;font-weight:400;color:#2D2D2D;padding-bottom:6px;mso-margin-bottom-alt:6px;text-decoration:none; }
.n p,
.n p a { font-size:12px;line-height:17px;font-weight:400;color:#2D2D2D;padding-bottom:6px;mso-margin-bottom-alt:6px;text-decoration:none; }
.p { background-color:#FFFFFF;max-width:520px;border:1px solid #E1E8ED;border:1px solid rgba(80, 80, 80, 0.3);border-radius:5px; }
.q { font-size:16px;font-family:Helvetica,Roboto,Calibri,sans-serif !important;border:1px solid #e1e8ed;border:1px solid rgba(80, 80, 80, 0.3);border-radius:10px;background-color:#FFFFFF; }
.q p { font-size:16px;font-family:system-ui,Helvetica,Roboto,Calibri,sans-serif !important;color:#222222;padding:4px 0; }
.r { border:1px solid #E1E8ED !important;border-radius:5px; }
.s p { font-size: 14px; line-height: 17px; font-weight: 400; color: #697882; text-decoration: none; }
.t p { font-family:'Helvetica',Arial,sans-serif;font-size:12px;line-height:18px;font-weight:400;color:#000000;font-style:italic;padding:4px 0px 0px; }
.v { border-radius:10px;border:solid 0px #DFD150;background-color:#2C81E5;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;color:#FFFFFF; }
.v a { text-decoration:none;display:block;color:#FFFFFF; }
.w p { font-size:12px;line-height:15px;font-weight:400;color:#FFFFFF; }
.w p a { text-decoration: underline !important;color:#FFFFFF !important; }
ul { font-family:'Helvetica',Arial,sans-serif;margin:0px 0px 0px 25px !important;padding:0px !important;color:#2D2D2D;line-height:24px;list-style:disc;font-size:16px; }
ul > li { font-family:'Helvetica',Arial,sans-serif;margin:10px 0px 0px 0px !important;padding: 0px 0px 0px 0px !important; color: #2D2D2D; list-style:disc; }
ol { font-family:'Helvetica',Arial,sans-serif;margin: 0px 0px 0px 25px !important;padding:0px !important;color:#2D2D2D;line-height:24px;list-style:decimal;font-size:16px; }
ol > li { font-family:'Helvetica',Arial,sans-serif;margin:10px 0px 0px 0px !important;padding: 0px 0px 0px 0px !important; color: #2D2D2D; }
.e h3,
.e p,
.e span { padding-bottom:0px;padding-top:0px;mso-margin-top-alt:0px;mso-margin-bottom-alt:0px; }
.e span,
.e li { font-family:'Helvetica',Arial,sans-serif;font-size:16px;color:#2D2D2D;line-height:24px; }
.rec { font-family: ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, "Noto Sans", sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji" !important; }
.rec__button:hover { background-color: #f9fafb !important; }
.copyright a {color: inherit !important; text-decoration: none !important; font-size: inherit !important; font-family: inherit !important; font-weight: inherit !important; line-height: inherit !important;}
.txt_social p { padding: 0; word-break: break-all; }
.table, .table-c, .table-h { border: 1px solid #C0C0C0; }
.table-c { padding:5px; background-color:#FFFFFF; }
.table-c p { color: #2D2D2D; font-family:'Helvetica',Arial,sans-serif !important;overflow-wrap: break-word; }
.table-h { padding:5px; background-color:#F1F1F1; }
.table-h p { color: #2A2A2A; font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif !important;overflow-wrap: break-word; }
@media only screen and (max-width:667px) {
.aa, .w100pc { width: 100% !important; }
.bb img { width: 100% !important; height: auto !important; max-width: none !important; }
.cc { padding: 0px 8px !important; }
.ee { padding-top:10px !important;padding-bottom:10px !important; }
.ff ul, .ff ol { margin: 0px 0px 0px 10px !important;padding: 0px !important; }
.ff li { margin:10px 0px 0px 10px !important; }
.r {height:140px !important;}
.s p { font-size:13px !important;line-height:15px !important; }
.mob-hide {display:none !important;}
.mob-show {display: block !important; width: auto !important; overflow: visible !important; float: none !important; max-height: inherit !important; line-height: inherit !important;}
.mob-stack {width:100% !important;display:block !important;}
.mob-w-full {width:100% !important;}
.mob-block {display:block !important;}
.embed-img {padding:0px 0px 12px 0px !important;}
.socialShare {padding-top:15px !important;}
.rec { padding-left:15px!important;padding-right:15px!important; }
.bodyWrapper { padding:7px 4px 7px 4px !important; }
.social-mobile {float:left !important;margin-top:10px !important;}
}
@media screen and (max-width: 480px) {
u + .a .gg { width: 100% !important; width: 100vw !important; }
.tok-heart { padding-top:75% !important; }
.tok-play { padding-top: 250px !important; }
}
@media screen and (max-width: 320px) {
.tok-heart { padding-top:65% !important; }
}
.u { border: 1px solid #CACACA !important; border-radius: 2px !important; background-color: #ffffff !important; padding: 0px 13px 0px 13px !important; font-family:ui-sans-serif,system-ui,-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans",sans-serif !important;font-size: 12px !important; color: #767676 !important; }
.u a { text-decoration: none; display: block !important; color: #767676 !important; margin: 0px !important; }
.u span, .u img { color: #767676 !important;margin:0px !important; max-height:32px !important;background-color:#ffffff !important; }
</style><!--[if mso]><style type="text/css">
h1, h2, h3, h4, h5, h6 {font-family: Arial, sans-serif !important;}
body, table, td, p, a, span {font-family: Arial, sans-serif !important;}
sup { font-size: 100% !important;vertical-align: .5em !important;mso-text-raise: -1.5% !important;line-height: 0 !important; }
ul { margin-left:0px !important; margin-right:10px !important; margin-top:20px !important; margin-bottom:20px !important; }
ul li { margin-left: 0px !important; mso-special-format: decimal; }
ol { margin-left:0px !important; margin-right:10px !important; margin-top:20px !important; margin-bottom:20px !important; }
ol li { margin-left: 0px !important; mso-special-format: decimal; }
li.listItem { margin-left:15px !important; margin-top:0px !important; }
.paddingDesktop { padding: 10px 0 !important; }
.edm_outlooklist { margin-left: -20px !important; }
.embedImage { display:none !important; }
</style><![endif]--><!-- __merge_tags_in_links__ --><style>
@font-face {
font-family: 'Open Sans';
font-style: normal;
font-weight: 700;
font-display: swap;
src: url('https://fonts.gstatic.com/s/opensans/v40/memSYaGs126MiZpBA-UvWbX2vVnXBbObj2OVZyOOSr4dVJWUgsg-1x4gaVIUwaEQbjA.woff2') format('woff2');
}
@font-face {
font-family: 'Open Sans';
font-style: italic;
font-weight: 700;
font-display: swap;
src: url('https://fonts.googleapis.com/css2?family=Open+Sans:ital,wght@1,700&display=swap') format('woff2');
}
</style></head><body class="a" style="margin:0px auto;padding:0px;word-wrap:normal;word-spacing:normal;background-color:#dedede;"><div role="article" aria-roledescription="email" aria-label="email_name" lang="en" style="font-size:1rem"><div style="display:none;max-height:0px;overflow:hidden;"> Plus more about StepWiser: Stepwise Generative Judges for Wiser Reasoning and Predicting the Order of Upcoming Tokens Improves Language Modeling  ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ </div><table role="none" width="100%" border="0" cellspacing="0" align="center" cellpadding="0" class="gg"><tr><td align="center" valign="top"><table role="none" width="670" border="0" cellspacing="0" cellpadding="0" class="aa" style="width:670px;table-layout:fixed;"><tr><td class="bodyWrapper" align="center" valign="top" style="padding:7px 7px 7px 7px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top" style="border-width:0px 0px 0px 0px;border-style: solid; border-color: #2a2a2a;border-radius:10px 10px 0px 0px;background-color:#ffffff;" class="c"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr id="header"><td style="padding:15px 15px 0px 15px;"><div style="padding-top:0px;padding-right:0px;padding-bottom:20px;padding-left:0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td class="f" align="right" valign="top"><p> September 03, 2025 | <a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.c6q0w4g5sodbtO4I1B_pxSdB5RCIH6yy1Fm1CYma3EyVm2vShVA4U9lW9CJFjjb0NYEk2ss7fRxbYp4jIPe7DzHHETvM_1_BbE7aYlRt6V1ftSsXJ8RHPuQW4VM45sbRetEEaxSMbRaw5W-xzEc61kUFjM5XXv7zFojyv7w9a_GGrLgMXyBt5fN6i0RCm9LjWw0kgZ676ruFnR8LN1MtXyCt9xpkNQA_UwSj3gt0btEB0SD44zw-fEZkRTMky5jN6NMtp1MuBSzQIkMviBXIdNmGTDCv3Jx1aUkN_lSeV57TxeYsFsV7EwX7T6AZj3GoGB1IdYETXY7wgnfcW4PUYqWaQVSVczEXDWySGa2WrlUQYcYadVlhZgFp9QPLoW0AtWQjAhNLmaExERkXEk-yK2ysaKaNXI0uGzukTuNbbCRBfU2ubEryF16PiOyaaQeQZY3cHjN0LFEKhq1V7S7G-XNGmG74j1hbsF2wLI9pVAqhXJWtBaNyfs7ELpOhNa_BkPLHHQBimoNOmeXGoMLySQ841IMrUTANjToQ1h840Nqen9XZZ2NpjLyCE3a_7TWhBLd6Uvh5Py87ngpkicLkV6eoQpMDV73muD8-lXDcOO-_KdxQx3ePyABdNCjWkCiZ-gm8IIKwcD1yKhUveSAWXEAF5e8qkhZlaJyv5P4G8iQMWj0oIL_eqqkYK_DraMD44Fd8hs7IlporMVgYiMVxgFQj2GDfV7FxKXjy6g3e9bU/4jl/Tdc078qCRgCTwz6XW_Ek8g/h0/h001.5VtV2qGeRd1wOXZidt3hilZUYkAE-rFdLLl9mzsppL4"><span class="translation_missing" title="translation missing: en.templates.posts.email.header.read_online">Read Online</span></a></p></td></tr><tr><td class="dd" align="center" valign="top" style="padding:15px 0;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top"><h1 style="text-align:left;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;font-weight:Bold;font-size:32px;color:#2A2A2A;padding:2px 0;line-height:38px;"> Prophesy in LLMs: DIFFUSION LANGUAGE MODELS KNOW THE ANSWER BEFORE DECODING </h1><p style="text-align:left;font-family:'Helvetica',Arial,sans-serif;font-weight:normal;font-size:20px;color:#3E3E3E;padding:5px 0;line-height:24px;"> Plus more about StepWiser: Stepwise Generative Judges for Wiser Reasoning and Predicting the Order of Upcoming Tokens Improves Language Modeling </p></td></tr></table></td></tr><tr><td style="line-height:0;"><div data-open-tracking="true"> <img src="https://elink4f7.mail.bycloud.ai/ss/o/u001.3wmUuY8gEWd4_869a_eXcg/4jl/Tdc078qCRgCTwz6XW_Ek8g/ho.gif" alt="" width="1" height="1" border="0" style="height:1px !important;width:1px !important;border-width:0 !important;margin-top:0 !important;margin-bottom:0 !important;margin-right:0 !important;margin-left:0 !important;padding-top:0 !important;padding-bottom:0 !important;padding-right:0 !important;padding-left:0 !important;"/> </div></td></tr></table></div></td></tr><tr id="content-blocks"><td class="email-card-body" align="center" valign="top" style="padding-bottom:28px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top" style="padding: 20px 28px 20px;" class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin: 0 auto 0 auto"><tr><td align="center" valign="top" style="width:300px;"><p style="opacity: 0.8;"><b>In partnership with</b></p></td></tr><tr><td align="center" valign="top" style="width:300px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jBFqPUFtyrTKI3nn0RVFRJyLj2MiYVWERjK1xAurc8E2Q2fS9ww5oRrbKVx1HtFkEmTpdF7PnJ9MyoNUIDdD9W0t3agzNmSJF_pyoG0HX2CpiZNQuzqKBdh3cXg1talXqfTwcXtxYZGK4naxCUsZ0gAsqtqniN4dBxCr55rnz4inPnhfwB24GkhLhMSgrHj8Eso9DMi_85ziPB11vxJQIfiHeeR4u_Iviea6A80pYez_HJyLXQJjOMTtxlXB8VokhyzBDSHmlUvPCoc6LDrGx9sGRJfkEOYNxStGvIe7u7RJi4L7xV2TvhtfRlK2V6yAXvl7GnV7C1g9I5yQnr7chfWPPiPWKjAPsF-ILDcBOL8YRjT8Bm1V4CJG36Cc1lcdjYzAAlHaJ_Og9Ze2cYdfDzUnre9gGF3yWJiq_mE04Wjjg/4jl/Tdc078qCRgCTwz6XW_Ek8g/h1/h001.7ty8PIrxE1IOPAV3bojQacqUi-o61QwQFXvL4_pA76I" target="_blank" rel="noopener noreferrer nofollow" style="text-decoration:none;"><img src="https://beehiiv-images-production.s3.amazonaws.com/uploads/ad_network/advertiser/logo/41d7583d-491a-4aff-b78d-375c2ac295a6/pacaso.png" height="auto" width="300" style="display:block;" lborder="0"/></a></td></tr></table></td></tr><tr><td id="nov-18-th-nov-24-th-33-latest-ai-re" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h6 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:87.5%;"><i>Aug 25th ~ Sep 2nd</i><br><i>#71 Latest AI Research Explained Simply</i></h6></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="#222222" style="background-color:#222222;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td id="industry-news-in-1-line" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:Bold;padding:0px 28px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:Bold;mso-line-height-alt:150.0%;">🗞️ Industry News in 1 Line</h2></td></tr><tr><td style="padding-bottom:12px;padding-left:50px;padding-right:40px;padding-top:12px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ol start="1" style="list-style-type:decimal;margin:0px 0px;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><span style="background-color:#e0e0e0;"><span style="color:rgb(255, 58, 58);font-size:0.6rem;">♥ 812</span></span> <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.CxDkkVpJsBdVoe83c_tBWlSeYJsO-zsxtfDNZO02yOFbnBkgz6YQWo2V2Xq1SkB05I3bSKyfGyN22Rp3bQXeNvHItocP3jd7VFDEb5wAn2JMzAW53Xj8m3L0MIdzMiA7VNKYZp8Fp1dBaPvR30ywSDru4lfdqXEpHUnWGJVE_B4/4jl/Tdc078qCRgCTwz6XW_Ek8g/h2/h001.ANCQx61KXlncSBWOIpjpvICxL7p4OZ30B2b2UJjRl3M" target="_blank" rel="noopener noreferrer nofollow"><span>Meituan has launched LongCat-Flash-Chat</span></a>, which was trained on 20T tokens. It uses 560B parameters and has a clever new ability: a "zero-computational expert" that allows it to ignore simple tokens and dynamically activate only a fraction of its brainpower. This innovative design lets it process information at over 100 tokens per second, so go ahead and <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.-a_uZGcEKk2OBxkkwsTf3ni-7oeAlN3YSd7b4iPzaaYI9OdG0suvsymQCaGcwshx-aWwtHe5E7skX9VXNzv8l4NkI4d3HWYUdaBHDcNztII/4jl/Tdc078qCRgCTwz6XW_Ek8g/h3/h001.mo9hSYDCrmnj_43ssgLJN-GgnYgat3C-b1SBapnD7NM" target="_blank" rel="noopener noreferrer nofollow"><span>try it out yourself</span></a>. </p><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/c4922aef-e620-41d4-b7e5-35c339c1205c/image.png?t=1756877910" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><span style="background-color:#e0e0e0;"><span style="color:rgb(255, 58, 58);font-size:0.6rem;">♥ 633</span></span> <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.CxDkkVpJsBdVoe83c_tBWoLE8R9BmZi5_D0_25nOCBqCi-m7Uu14e1-tc5pz3SRxkFF6d1bW7fysG8rr-Xb49K1SJJWQx655ixpoSUHddC0UH7DCh9I7zQwfJEQ4irBvNPibzruaJcrOzesJWAHvgg/4jl/Tdc078qCRgCTwz6XW_Ek8g/h4/h001.KJr2auvj0NgM7TWMw20qHuTTMLfcBrbrTGTDD_Ept88" target="_blank" rel="noopener noreferrer nofollow"><span>NVIDIA has released Nemotron-CC-v2</span></a>, which is a massive dataset that breathes new life into web crawl data by using models like Qwen3 to synthetically generate rephrased text and diverse Q&A, which is then <b>translated into 15 languages</b>. This open-source dataset also features a specialized pipeline that preserves math equations in LaTeX and a huge corpus of curated code, complete with its own synthetically generated Q&A. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><span style="background-color:#e0e0e0;"><span style="color:rgb(255, 58, 58);font-size:0.6rem;">♥ 873</span></span> <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.VomAAYwkCjux8i_FMc4kJWTmyQmrre3Ms0j3HogriTlaNvOpsScllRlivh8YAfVsIV0mrQgUkfc_zafS5p6gRRPmhE05erVbBzSTC8NKZseqFVdcrR1mW7GNpaoJV-2k/4jl/Tdc078qCRgCTwz6XW_Ek8g/h5/h001.Z_MDl9PpJ55dKjQWFbQgV0W_YX-sLL-xEzVfgvk_oHM" target="_blank" rel="noopener noreferrer nofollow"><span>Intern-S1</span></a> is a new open-source model that combines a huge 235B parameter language model with a vision encoder. It is trained on a massive 5-trillion-token dataset with a heavy focus on scientific material. This specialized training gives it a unique ability to understand complex inputs like molecular formulas and protein sequences directly. You can <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.ZsobsZmG6kUZ4LjqczYBVFKXhv_r-ncTUNArJcbNVUbNarfimFU1QygTow0XYej494KzxSMFg1ItwCEdJ2z1lY8ffD1W_X6gyGEGWdEaKTG2yMFeHAuOf8Ps-zTnM9My/4jl/Tdc078qCRgCTwz6XW_Ek8g/h6/h001.qGSWeYHFmTHWH5_c-Z3eGkN_r7yO3OKD-yhkeYtOCwY" target="_blank" rel="noopener noreferrer nofollow"><span>try Intern-S1 on the web</span></a> or use it via API. </p><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/991f89b6-5fe4-439d-9139-3a91633392de/image.png?t=1756878781" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></li></ol></div></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="#222222" style="background-color:#222222;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td id="how-433-investors-unlocked-400-x-re" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">How 433 Investors Unlocked 400X Return Potential</h3></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jBFqPUFtyrTKI3nn0RVFRJyLj2MiYVWERjK1xAurc8E2Q2fS9ww5oRrbKVx1HtFkEmTpdF7PnJ9MyoNUIDdD9W0t3agzNmSJF_pyoG0HX2CpiZNQuzqKBdh3cXg1talXqfTwcXtxYZGK4naxCUsZ0gAsqtqniN4dBxCr55rnz4inPnhfwB24GkhLhMSgrHj8Eso9DMi_85ziPB11vxJQIfiHeeR4u_Iviea6A80pYez_HJyLXQJjOMTtxlXB8VokhyzBDSHmlUvPCoc6LDrGx9sGRJfkEOYNxStGvIe7u7RJi4L7xV2TvhtfRlK2V6yAXvl7GnV7C1g9I5yQnr7chfWyRLY6StEQeZSTlTPgLdtPEH1Qqei2T32XptWubWIuomHxkF-ZjOD8ML7rI1upLTDclhCO6FvIojShfzsvcNKew/4jl/Tdc078qCRgCTwz6XW_Ek8g/h7/h001.KRYcbWMJCVaVHxfsdYVs1DHQ2VHQMfib6hK_KECgzJ0" rel="noopener noreferrer nofollow" style="text-decoration:none;" target="_blank"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/e25212e5-75ec-42b0-984d-7d989b4fcc6a/4_Pacaso_Partnerships-1200x600_070225_002.png?t=1755879860" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></a></td></tr></table></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Institutional investors back startups to unlock outsized returns. Regular investors have to wait. But not anymore. Thanks to regulatory updates, some companies are doing things differently. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Take Revolut. In 2016, 433 regular people invested an average of $2,730. Today? They got a 400X buyout offer from the company, as Revolut’s valuation increased 89,900% in the same timeframe. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> No wonder <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jBFqPUFtyrTKI3nn0RVFRJyLj2MiYVWERjK1xAurc8E2Q2fS9ww5oRrbKVx1HtFkEmTpdF7PnJ9MyoNUIDdD9W0t3agzNmSJF_pyoG0HX2CpiZNQuzqKBdh3cXg1talXqfTwcXtxYZGK4naxCUsZ0gAsqtqniN4dBxCr55rnz4inPnhfwB24GkhLhMSgrHj8Eso9DMi_85ziPB11vxJQIfiHeeR4u_Iviea6A80pYez_HJyLXQJjOMTtxlXB8VokhyzBDSHmlUvPCoc6LDrGx9sGRJfkEOYNxStGvIe7u7RJi4L7xV2TvhtfRlK2V6yAXvl7GnV7C1g9I5yQnr7chfW_kw4HwNnYl1o5K989djPkeWBp5NeZrz6dqul_cqNv4xwO-wDaDOp9KA5IW0GJq0Y0cU_IZzln_49JJlzF8kvAg/4jl/Tdc078qCRgCTwz6XW_Ek8g/h8/h001.Mxtmr5RtSgb2fUICXM3y5pQFc6QOe2rIE2aLtHI9Jgw" target="_blank" rel="noopener noreferrer nofollow"><span>10K+ everyday people are taking the chance on Pacaso. </span></a></p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Founded by a former Zillow exec, <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jBFqPUFtyrTKI3nn0RVFRJyLj2MiYVWERjK1xAurc8E2Q2fS9ww5oRrbKVx1HtFkEmTpdF7PnJ9MyoNUIDdD9W0t3agzNmSJF_pyoG0HX2CpiZNQuzqKBdh3cXg1talXqfTwcXtxYZGK4naxCUsZ0gAsqtqniN4dBxCr55rnz4inPnhfwB24GkhLhMSgrHj8Eso9DMi_85ziPB11vxJQIfiHeeR4u_Iviea6A80pYez_HJyLXQJjOMTtxlXB8VokhyzBDSHmlUvPCoc6LDrGx9sGRJfkEOYNxStGvIe7u7RJi4L7xV2TvhtfRlK2V6yAXvl7GnV7C1g9I5yQnr7chfWQaQmz0Q6V5lFv9iEiiZqO4v_-BJhHaQHsrG1Zci7ckEAg7YBIREkj0czOgcpZFa9PtcArzRZ_WFE4xx-jtKuVw/4jl/Tdc078qCRgCTwz6XW_Ek8g/h9/h001.38oKAp9UtyhLwtHO5L8qWBXsYqT-ZuCMxIki6kvKRUA" target="_blank" rel="noopener noreferrer nofollow"><span>Pacaso’s</span></a> co-ownership tech reshapes the $1.3T vacation home market. They’ve earned $110M+ in gross profit to date, including 41% YoY growth in 2024 alone. They even reserved the Nasdaq ticker PCSO. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> The same institutional investors behind Uber, Venmo, and eBay backed Pacaso. And you can join them. But not for long. <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jBFqPUFtyrTKI3nn0RVFRJyLj2MiYVWERjK1xAurc8E2Q2fS9ww5oRrbKVx1HtFkEmTpdF7PnJ9MyoNUIDdD9W0t3agzNmSJF_pyoG0HX2CpiZNQuzqKBdh3cXg1talXqfTwcXtxYZGK4naxCUsZ0gAsqtqniN4dBxCr55rnz4inPnhfwB24GkhLhMSgrHj8Eso9DMi_85ziPB11vxJQIfiHeeR4u_Iviea6A80pYez_HJyLXQJjOMTtxlXB8VokhyzBDSHmlUvPCoc6LDrGx9sGRJfkEOYNxStGvIe7u7RJi4L7xV2TvhtfRlK2V6yAXvl7GnV7C1g9I5yQnr7chfWnP2GD0idEeJ__c3K91M0zpv9s3UxvuY7d2ExMvRYHjUhov9OLRNEMUYRUnsPv44pZ30zXbhxQJuG8JB-Vr9PGg/4jl/Tdc078qCRgCTwz6XW_Ek8g/h10/h001.3D0esisv8-OG2np1ox6wc1Gg8C9kGRkMWPHDmJfufUI" target="_blank" rel="noopener noreferrer nofollow"><span>Pacaso’s investment opportunity ends September 18.</span></a></p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jBFqPUFtyrTKI3nn0RVFRJyLj2MiYVWERjK1xAurc8E2Q2fS9ww5oRrbKVx1HtFkEmTpdF7PnJ9MyoNUIDdD9W0t3agzNmSJF_pyoG0HX2CpiZNQuzqKBdh3cXg1talXqfTwcXtxYZGK4naxCUsZ0gAsqtqniN4dBxCr55rnz4inPnhfwB24GkhLhMSgrHj8Eso9DMi_85ziPB11vxJQIfiHeeR4u_Iviea6A80pYez_HJyLXQJjOMTtxlXB8VokhyzBDSHmlUvPCoc6LDrGx9sGRJfkEOYNxStGvIe7u7RJi4L7xV2TvhtfRlK2V6yAXvl7GnV7C1g9I5yQnr7chfWdQ8zvdtxe-hZ7H4JmVmzmZQIylabGHwnebIh63QE85umS953weIFb0dwukFqyfQ34vb65Q0gPvuvY_r2rB5pUA/4jl/Tdc078qCRgCTwz6XW_Ek8g/h11/h001.4zWuLzaVM5X8fWozkW1SWnWeptTuenGCI9cO-fktidI" target="_blank" rel="noopener noreferrer nofollow"><span>Invest While You Still Can</span></a></p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><sub>Paid advertisement for Pacaso’s Regulation A offering. Read the offering circular at </sub><sub><a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.cu66jm18t41dYHNTTOnr7JhOxzgrQX4h1LYYbHYd0jD6QxFMyeRWRSOyfN--DTuVLOc0AzcBYLh3YokBdtBxDX6qiy35ubvIVxI2wqMamV8l2LlAdvWs_wZaZ3tFB12o/4jl/Tdc078qCRgCTwz6XW_Ek8g/h12/h001.qA3NuDPQyGDOvFL2PtQrzAw_DucAuvYN4tFOtXZtLf8" target="_blank" rel="noopener noreferrer nofollow"><span>invest.pacaso.com</span></a></sub><sub>. Reserving a ticker symbol is not a guarantee that the company will go public. Listing on the NASDAQ is subject to approvals. </sub></p></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="#222222" style="background-color:#222222;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td id="predicting-the-order-of-upcoming-to" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:Bold;padding:0px 28px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:Bold;mso-line-height-alt:150.0%;">Predicting the Order of Upcoming Tokens Improves Language Modeling</h2></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><i>Zuhri</i><span style=""><i> et al. [</i></span><i>MBZUAI</i><span style=""><i>]</i></span></p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style="background-color:#e0e0e0;"><span style="color:rgb(255, 58, 58);font-size:0.6rem;"> ♥ 563 </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </span><span style="background-color:#e0e0e0;"><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> LLM Tokenization </span></span></p></td></tr><tr><td id="introduction-to-token-order-predict" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Introduction to Token Order Prediction</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> LLMs are trained to predict the next word in a sequence. This approach has a few limitations; it doesn’t always help models reason about longer contexts or future words. Multi-token prediction (MTP) was introduced to improve this by having models predict several future tokens at once. However, MTP has shown inconsistent results, and it often underperforms on standard language tasks. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> This paper introduces Token Order Prediction (TOP), which trains the model to learn the order of upcoming tokens based on their proximity instead of asking it to predict specific future tokens. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/fba3e6d1-1741-4d52-8cf0-b4a39f8da724/image.png?t=1756840458" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:626px; padding: 4px 0px 4px 0px;"><p>An overview of Token Order Prediction (TOP).</p></td></tr></table></td></tr><tr><td id="inner-workings-of-token-order-predi" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Inner Workings of Token Order Prediction</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> TOP works by training the model to rank tokens based on how soon they appear after the current position in a sequence. For a given input, the model learns to assign higher scores to tokens that appear sooner and lower scores to those that appear later. This is done using a learning-to-rank loss function adapted from information retrieval, which compares the model’s predicted ranking with the actual order of tokens in the training data. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Unlike MTP, which requires adding multiple transformer layers for each future token prediction, TOP only needs one additional linear layer (the TOP head) alongside the standard next-token prediction head. Both heads use the same hidden representations from the transformer, making the approach parameter-efficient and easy to integrate. During training, the model optimizes a combined loss from both the next-token and token-order prediction tasks. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/06d87aef-b397-49de-9d76-a92ebca6baa2/image.png?t=1756840609" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> This design allows the model to develop a richer understanding of sequence structure without overcomplicating the learning process. By focusing on relative order rather than exact token identity, TOP encourages the model to form representations that are more aware of context and future dependencies, which in turn improves its ability to predict the next token accurately. </p></td></tr><tr><td id="evaluation-and-performance-of-token" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Evaluation and Performance of Token Order Prediction</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> The researchers tested TOP against both standard NTP and MTP across three model sizes: 340 million, 1.8 billion, and 7 billion parameters. The results showed that TOP consistently outperformed both NTP and MTP across most tasks and improvements were more noticable as model size increased. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/6223c58c-ddfb-4ddf-ab8d-0186a82309bf/image.png?t=1756840518" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:626px; padding: 4px 0px 4px 0px;"><p>General language modeling evaluation results of NTP vs MTP vs TOP on standard NLP benchmarks.</p></td></tr></table></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> For example, the 7B TOP model achieved higher accuracy on Lambada, HellaSwag, and TriviaQA compared to baselines. It also had better scaling behavior than MTP, which often struggled on non-coding tasks. Interestingly, TOP models had a slightly higher training loss on the next-token prediction task but still generalized better, which suggests that TOP acts as a regularizer that prevents overfitting. </p></td></tr><tr class="btn_row"><td valign="top" style="padding-bottom:14px;padding-left:28px;padding-right:28px;padding-top:14px;text-align:center;width:100%;word-break:break-word;" class="dd"><table width="100%" role="none" border="0" cellspacing="0" cellpadding="0" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle"><table role="none" border="0" cellspacing="0" cellpadding="0"><tr><td style="background-color:#2C81E5;border-radius:8px;mso-padding-alt:14px 20px;" class="btn"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.fUNb4GdFo9D3F8WuLArtoV5sElgytBlvJRzI9WtI92bC-OLBXLS68tmCkxHBsIVuNIOADVyG2szRmcOoLGdlEvFPR6ZOJDfk7nekxrC91O1fNWYa2iIZhXCTq3WgtJMT/4jl/Tdc078qCRgCTwz6XW_Ek8g/h13/h001.li3IdZpNGi_bzvmC-Mau447GwtpTac5mV3mZ-j5t3_c" target="_blank" rel="noopener noreferrer nofollow" style="background-color:#2C81E5;border-radius:8px;color:#FFFFFF;display:inline-block;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;font-size:16px;font-weight:normal;line-height:18px;padding:14px 20px;text-decoration:none;"> Read Full Paper </a></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="#222222" style="background-color:#222222;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td id="janus-pro-unified-multimodal-unders" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:Bold;padding:0px 28px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:Bold;mso-line-height-alt:150.0%;">StepWiser: Stepwise Generative Judges for Wiser Reasoning</h2></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><i>Xiong et al. [FAIR at Meta, University of Illinois Urbana-Champaign, NYU]</i></p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style="background-color:#e0e0e0;"><span style="color:rgb(255, 58, 58);font-size:0.6rem;"> ♥ 480 </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </span><span style="background-color:#e0e0e0;"><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> LLM Reasoning </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </span></p></td></tr><tr><td id="introduction-to-stepwise-generative" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Introduction to Stepwise Generative Judges</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> As LLMs rely on multi-step reasoning strategies like Chain-of-Thought to tackle complex problems. Supervising these intermediate steps for logical correctness has become a major challenge. Existing process reward models often act as black-box classifiers, and they offer scores without explanations. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> This paper has reframed stepwise reward modeling from a classification task to a reasoning task. This led to the development of STEPWISER, which is a generative judge that meta-reasons about reasoning steps before delivering a verdict. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/459b5382-e5d3-40fc-93d0-3ae94bc990cf/image.png?t=1756840865" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:626px; padding: 4px 0px 4px 0px;"><p>Overview of our STEPWISER training method.</p></td></tr></table></td></tr><tr><td id="inner-workings-of-stepwiser" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Inner Workings of STEPWISER</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> STEPWISER has three key components. </p></td></tr><tr><td style="padding-bottom:12px;padding-left:50px;padding-right:40px;padding-top:12px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ol start="1" style="list-style-type:decimal;margin:0px 0px;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> First, it uses self-segmentation to break reasoning chains into coherent chunks, called Chunks-of-Thought. This is done by fine-tuning the base model to identify logical segments based on rules like unified purpose and clear transitions, ensuring each chunk represents a complete step in the problem-solving process. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> Next, each chunk is annotated with a binary label indicating whether it is helpful or harmful. This is done by estimating Q-values through Monte Carlo rollouts, i.e., generating multiple completions from each step and calculating the average success rate. To better capture progress, methods like relative effective reward thresholding compare success rates before and after a chunk, rewarding improvements rather than just absolute correctness. </p></li></ol></div></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/cd62a3af-bca3-4c11-ab2b-275cd291eb60/image.png?t=1756840897" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td style="padding-bottom:12px;padding-left:50px;padding-right:40px;padding-top:12px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ol start="3" style="list-style-type:decimal;margin:0px 0px;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> Finally, the judge model is trained with reinforcement learning to generate its own reasoning about each chunk before outputting a judgment. It uses a reward based on alignment with the estimated labels and techniques like GRPO for optimization. Prompt balancing is used to ensure stable training by equalizing positive and negative examples. </p></li></ol></div></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/dcd6dd9b-6151-4ca3-9fdf-9f749ac04c51/image.png?t=1756840955" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td id="evaluation-and-impact-of-stepwiser" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Evaluation and Impact of STEPWISER</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> STEPWISER significantly outperforms existing methods on ProcessBench (a benchmark for identifying incorrect reasoning steps). It also excels in practical applications like inference-time search, where it guides models to discard flawed chunks and retry, leading to better final solutions. Moreover, when it is used for training data selection, it helps identify high-quality reasoning traces and improves downstream model performance through fine-tuning. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/14c31275-431a-409e-9296-5171bde53215/image.png?t=1756841017" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr class="btn_row"><td valign="top" style="padding-bottom:14px;padding-left:28px;padding-right:28px;padding-top:14px;text-align:center;width:100%;word-break:break-word;" class="dd"><table width="100%" role="none" border="0" cellspacing="0" cellpadding="0" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle"><table role="none" border="0" cellspacing="0" cellpadding="0"><tr><td style="background-color:#2C81E5;border-radius:8px;mso-padding-alt:14px 20px;" class="btn"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.fUNb4GdFo9D3F8WuLArtoV5sElgytBlvJRzI9WtI92YE9G88BXDZji18jHh3pqgQGOzeHn7GDhDkGSlw1J850PFdj_yqAGNPBPGlRqMbrZfA119Hgu6Bc8Cf2ni7S35t/4jl/Tdc078qCRgCTwz6XW_Ek8g/h14/h001.Lloy0UXhCtovMXzwsF7d2SltOO30CB4TLTHYVpG3eq8" target="_blank" rel="noopener noreferrer nofollow" style="background-color:#2C81E5;border-radius:8px;color:#FFFFFF;display:inline-block;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;font-size:16px;font-weight:normal;line-height:18px;padding:14px 20px;text-decoration:none;"> Read Full Paper </a></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="#222222" style="background-color:#222222;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td id="diffusion-language-models-know-the-" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:Bold;padding:0px 28px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:Bold;mso-line-height-alt:150.0%;">DIFFUSION LANGUAGE MODELS KNOW THE ANSWER BEFORE DECODING </h2></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><i>Li et al. [The Hong Kong Polytechnic University, Dartmouth College, University of Surrey, Sun Yat-sen University</i>, <i>Google DeepMind, Max Planck Institute for Intelligent Systems, ELLIS Institute Tubingen]</i></p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style="background-color:#e0e0e0;"><span style="color:rgb(255, 58, 58);font-size:0.6rem;"> ♥ 226 </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </span><span style="background-color:#e0e0e0;"><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> LLM Diffusion </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </span><span style="background-color:#e0e0e0;"><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> bycloud’s pick </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </span></p></td></tr><tr><td id="introduction-to-early-answer-conver" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Introduction to Early Answer Convergence in Diffusion Language Models</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Diffusion language models are gaining attention as a flexible alternative to autoregressive models. However, one major drawback has been their slower inference speed, largely because they require multiple refinement steps and use bidirectional attention. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> This paper has uncovered an interesting behavior in these models: the correct answer often appears internally well before the decoding process finishes. For instance, on benchmarks like GSM8K and MMLU, up to 97% and 99% of answers can be correctly identified using only <b>half the usual steps</b>. This observation led to the development of <b>Prophet</b>, a method that uses early commit decoding to speed up inference without extra training. </p></td></tr><tr><td id="inner-working-of-prophets-early-com" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Inner Working of Prophet’s Early Commit Decoding</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Prophet works by monitoring the confidence of the model’s predictions during each decoding step. It calculates the confidence gap (the difference between the top two predicted tokens) at every position. A large gap indicates that the model is highly certain about a token, which suggests it may not change in future steps. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/e46755a9-a7a8-43f9-9908-472d77fc0c7f/image.png?t=1756841382" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Based on this gap, Prophet decides dynamically whether to continue refining or to finalize all remaining tokens at once. It uses a threshold that changes as decoding progresses: early on, it requires a very high confidence level to commit, reducing the risk of errors. Later, as predictions stabilize, it allows for earlier termination. This approach integrates smoothly into existing diffusion model setups and <b>adds almost no computational overhead</b>. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/3bb6479c-1e50-4f5a-b1da-bf40d9e3d928/482250393-2c78909a-89bd-497c-8288-fe5539f8edb2.png?t=1756841327" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:626px; padding: 4px 0px 4px 0px;"><p>An illustration of the Prophet’s early-commit-decoding mechanism.</p></td></tr></table></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> The process is fully adaptive and <b>requires no retraining</b>, which makes it easy to apply to models like LLaDA-8B or Dream-7B. By focusing on answer tokens and leveraging their early convergence, Prophet significantly cuts down the number of decoding steps while preserving output quality. </p></td></tr><tr><td id="evaluation-and-performance-of-proph" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:125.0%;">Evaluation and Performance of Prophet</h3></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> The researchers performed experiments across multiple benchmarks and showed that Prophet <b>reduces decoding steps by up to 3.4 times</b> with minimal loss in accuracy. For example, Prophet nearly matches the performance of full-step decoding in general reasoning tasks like MMLU and ARC-Challenge. In some cases, it even slightly outperforms the baseline, possibly by avoiding unnecessary refinement that could introduce noise. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/413afc55-2421-4466-95a4-ba3423fc492d/image.png?t=1756841358" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:626px; padding: 4px 0px 4px 0px;"><p>Distribution of early correct answer detection during decoding process.</p></td></tr></table></td></tr><tr><td class="dd" align="left" style="padding:0px 28px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> On more demanding tasks like mathematical reasoning (GSM8K) and science questions (GPQA), Prophet maintains close to full accuracy while the naive half-step baseline often drops significantly. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:15px;padding-right:15px;padding-top:20px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:626px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/c8cb5d52-cba0-4519-bbba-035d45071a56/image.png?t=1756841415" alt="" height="auto" width="626" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:626px; padding: 4px 0px 4px 0px;"><p>Benchmark results on LLaDA-8B-Instruct and Dream-7B-Instruct.</p></td></tr></table></td></tr><tr class="btn_row"><td valign="top" style="padding-bottom:14px;padding-left:28px;padding-right:28px;padding-top:14px;text-align:center;width:100%;word-break:break-word;" class="dd"><table width="100%" role="none" border="0" cellspacing="0" cellpadding="0" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle"><table role="none" border="0" cellspacing="0" cellpadding="0"><tr><td style="background-color:#2C81E5;border-radius:8px;mso-padding-alt:14px 20px;" class="btn"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.fUNb4GdFo9D3F8WuLArtoV5sElgytBlvJRzI9WtI92Z3Yj0SX9kgfQsWBpRD49FCdll4Ho1DlsW2uvL8MrkHgE2-fbT0pl45LG1Ff9knc9xQ7PIZnFVp4dJPPkilHm0H/4jl/Tdc078qCRgCTwz6XW_Ek8g/h15/h001.sBhkUm8tyCmlE6yTZu7K33RDZsPSQ9J5NhWOhY_Cj7U" target="_blank" rel="noopener noreferrer nofollow" style="background-color:#2C81E5;border-radius:8px;color:#FFFFFF;display:inline-block;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;font-size:16px;font-weight:normal;line-height:18px;padding:14px 20px;text-decoration:none;"> Read Full Paper </a></td></tr></table></td></tr></table></td></tr><tr><td class="dd" align="center" valign="top" style="padding:20px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.amatuKKICSickUKplYJXmFiNByCcuMoGQrfaEppQaeTnoqPQa-vXyMJrDy5k_cMSTTdU9_UtzS7Hd6ePWZ-F0QoaCASScgSgLdAt3-hEBUTGzmgQnIk_ehQYb-D3iguKI2Z3MTAmahqsT6BLUV6pjw/4jl/Tdc078qCRgCTwz6XW_Ek8g/h16/h001.BQMn4WMMJaFc16pa8d6a0WjOKQXq9LLnAPYc1yQhTG8" style="text-decoration:none;"><table align="center" width="100%" cellpadding="0" cellspacing="0" border="0" role="none" style="max-width:520px;margin:0 auto;"><tr><td class="p" width="100%" style="padding:2px;border:none;"><table width="100%" cellpadding="0" cellspacing="0" border="0" role="none"><tr><td align="center" valign="top" style="width:100%;"><div style="max-height:0;position:relative;opacity:0.999;width:100%;mso-hide:all;"><div style="display:inline-block;width:100%;padding-top:25%;"><img width="20%" height="auto" loading="lazy" alt="" style="border:0;" src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/static_assets/youtube_play_icon.png"/></div></div><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.amatuKKICSickUKplYJXmFiNByCcuMoGQrfaEppQaeTnoqPQa-vXyMJrDy5k_cMSPSlXomFwE389PCsMq6DZXTVI8Uv4KiEbQ__JPCuSWUGN4PhVsK-cMlwpZGqWxmW6Vry1nC1iJL3B15-l3w9-dg/4jl/Tdc078qCRgCTwz6XW_Ek8g/h17/h001.Vmayw84TUF2OBXxnWA_DHLjGg28k3rQD-6kLk7GezC4" style="text-decoration:none;"><img src="https://i.ytimg.com/vi/uOrJUksvIhs/maxresdefault.jpg" width="480" height="auto" loading="lazy" alt="YouTube video by bycloud" style="display:block;height:auto;border:0;outline:none;text-decoration:none;background-color:#000000;width:100%;"/></a></td></tr><tr><td><p style="font-size:12px;font-weight:500;font-style:italic;font-family:Helvetica, Calibri, sans-serif;color: #686a6d; padding-top:0 !important;padding-bottom:6px !important; padding-left:4px !important;"> What if we train LLMs with "Pathfinding"? </p></td></tr></table></td></tr></table></a></td></tr></table></td></tr></table></td></tr><tr><td align="center" valign="top"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td><tr><td class="b" align="center" valign="top" bgcolor="#2a2a2a" style="padding:0px 0px 0px 0px;border-style:solid;border-width: 0px 0px 0px 0px;border-color: #2a2a2a;border-bottom-left-radius:10px;border-bottom-right-radius:10px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top" bgcolor="#73ddff" style="padding:12px"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td><span style="padding-left:1px;"></span></td><td align="center" valign="middle" width="75" style="width:75px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.1muhFWIqieRYpaJ-FbWSCQqcWoV4NNHHr5SkP9THApWuHAAlWLQxI3Q_IqFmt_DcyAxeC8jDApCnHmMSBGpBb5sgtimvBYgxRX-Rp7s0F3LjCHoSwdhr83OBqRFhJ1y_/4jl/Tdc078qCRgCTwz6XW_Ek8g/h18/h001.KtY-zzjsz9QPm54e9FG5KzkedDlVj2t9G_J-7-LplpU" style="text-decoration:none;"><img width="22" height="22" alt="tw" border="0" style="display:block;max-width:22px;color:Dark" src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/static_assets/x_dark.png"/></a></td><td align="center" valign="middle" width="75" style="width:75px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.amatuKKICSickUKplYJXmBoQnQ9VXnB2zTxBG4HeHBgjMqVxpoXRdj01cjwyoVlHgiebEOgBvwHtevoVpsSvpn3Q1di2ml6sb3cBM-X6IStQbj_zQSVGWJ8AAmPw2en2/4jl/Tdc078qCRgCTwz6XW_Ek8g/h19/h001.jPofV9aC7-UeNy_C-LiZb7O52qXdQCgqqHBxRC-uNmM" style="text-decoration:none;"><img width="22" height="16" alt="yt" border="0" style="display:block;max-width:22px;color:Dark" src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/static_assets/youtube_dark.png"/></a></td><td><span style="padding-left:1px;"></span></td></tr></table></td></tr><tr><td height="10" style="line-height:1px;font-size:1px;height:10px;"> </td></tr><tr><td class="w" align="center" valign="top" style="padding:15px 15px 15px 15px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top"><p style="font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF!important;"> Update your email preferences or unsubscribe <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.c6q0w4g5sodbtO4I1B_pxWc4htTObwdorovK0nFHVH-4pUdVE0ELYH5DsNemk732SjNwhPNJ25r0O8B5vYifsBhEpz-DJgyVFmavJPa0OyKRRnvw4o7XGyvIv7PRofnmygnbXVxjTm2bi5re0IrewMEvZeNd-46nqPLiinHASWplx9wBGiROrt0zfUm0oXsQmMuq74DpUOu2SnZK9-GLp26ftkBBvcVTB_XCktl6WgxkyngLY3-7681WXlpg3DkbK53p42ZHR7q9xJxqfdtCQvoKwJ7v8T3rZHUm2Rz9c5cl9pI-xvlNFSU6D9bceje8icobjq0RGpWeufgwG8l6D8N96tIzxf9-L_w-iFw7UNna83IHS2RzACQjdzce-vPaeF9bkdmhK9Y5c980ok9wg-KbSwD8xeVLYH4wFIQkN9xNB4Uu_eZ7gyrGxhsF4tLK7FwFoG3iNogx4IJZgH9xvJaoyoxPZnlezVqI2PKbcuxNbiIsnkkjS2jpBMbgKoFuUaRgllyRb3pmdsm9NzUrkTqKjzAHE2bYAcNwoJAPWO4Yl-OL8wsZ0a4DVxihHLciRrGj_8IyqUxRCOexS6Y4e82YBSuvOiMjxWj13EFM7Bh99R6JvW0KWLqh8-8JdU4jA9ElN05NCKOlODhUnoGjNKtM_rxobYumXjN9xXurbBIe9eU8wjOaTC8WikkQrgQJtDMJGMogrRuBNG8iKpOgaa7UYiQA-2JJ7hYQAMze3SzKp3nRkzZamSzBff9W2DRG_rP0lPFTfssVrsaWpQ7n1F_AquUtx8KC_Nfeby6kxe_tJVk_wdFIM7M6GR4fWViA1-CRAnaPELgjkkmGyv0CEQ/4jl/Tdc078qCRgCTwz6XW_Ek8g/h20/h001.fZuXYJyFq-1Oo9gvy0evuWqnoirq_765xIPMjBeG2No" style="text-decoration:underline;text-decoration-color:#FFFFFF!important;color:#FFFFFF!important;"> here</a></p><p class="copyright" style="font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF!important;"> © 2025 bycloudai </p><p style="font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF!important;"> 228 Park Ave S, #29976, New York, New York 10003, United States </p></td></tr><tr style="display: table-row !important;"><td align="center" valign="top" style="padding-top:20px;" style="display:table-cell !important;"><table role="none" border="0" cellspacing="0" cellpadding="0" align="center" style="display:table !important;"><tr style="display:table-row !important;"><td class="u" align="center" valign="middle" height="32" style="height:32px;display:table-cell !important; max-height: 32px !important;margin:0px !important; background-color: #ffffff !important;"><a style="line-height:32px !important;text-decoration:none;display:block !important;" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.DUiN96-Eq7pUHzwEhy5j28olDWFpV5DDKfdk_OdOKOgL3Cz38fK8ApCxLRobInlPQQ3Oqjz_0TlFnIEX5N4B4lI7RQfbkNRZGRe4p1fJzZR1xGPAcBavhwJaERPBAwLZ3N-YNo7NN1o-PWExAJZFfdEul-nAWmCGSh7XOQx17CWAGS2HVFLFKyWprqjoqwsSFSJJ2K2P02FpXhxXpK-bcVdGQ7zTEwtS-5iuNXtI-8BRC7SMJMNAAcGbFmItDqNR/4jl/Tdc078qCRgCTwz6XW_Ek8g/h21/h001.SFrNCDMYdhwDiybaGSLukWLfS__ie_W0wRBgr2CLAik"><img src="https://media.beehiiv.com/output-onlinepngtools.png" width="16" alt="beehiiv logo" style="display:inline-block !important;max-width:16px !important; vertical-align:-3px !important;width: 16px !important;" border="0"/><span style="padding-left:11px !important;display: inline-block !important;">Powered by beehiiv</span></a></td></tr></table></td></tr><tr><td align="left" valign="top" height="2" style="height:2px;"><a href='https://elink4f7.mail.bycloud.ai/ss/c/u001.CxDkkVpJsBdVoe83c_tBWsHIaP4XNp0WgUYqLvHcKk_3uqk_KIkz4ddLinhFbud6JuxLFdSUhYnR7b1NSsmbtzXNGNblnEEMKUtkCAjkn8Y/4jl/Tdc078qCRgCTwz6XW_Ek8g/h22/h001.QG-kPta70iVjp1Vj9PJ8BkT9359tncON7zzG-MBRCz8' style="color: #2a2a2a !important; cursor: default; font-size: 1px; text-decoration: none;"> Terms of Service </a></td></tr></table></td></tr></table></td></tr></td></tr></table></td></tr></table></td></tr></table></td></tr></table></div></body></html>