<!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>Absolute Zero: Reinforced Self-play Reasoning with Zero Data</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 { 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; list-style:decimal; } .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 { 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-stack {display:block !important;width:100% !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"> 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]--><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 Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction and RM-R1: Reward Modeling as Reasoning  ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ </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:28px 28px 0px 28px;"><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> May 13, 2025 | <a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.c6q0w4g5sodbtO4I1B_pxSdB5RCIH6yy1Fm1CYma3Ey82mwmXcYCj6bKCvbdFpVrxKWxLfImtJ-fQKnO07MIS3loJYAW3QVk6KNxdhzkKB3RyT1A-hhAPfCcyK-1drDunm8-qEw-VwNBL7Mmq8K9cpwauozvFQJPSfPFat_jrtwtI-nI3k9Ji_JbmMSDtqpawMkwOyvJMJwIpLx4nPOVRJGmzB4edC4N-GjYgm_opihbLWoFDkgkKPEdCBfUm07FQVSnJ7obvQ4P8eZ5t_G7vqpo6Kw9hW6Y4oy3ltJhcavLdwGE0nJFgNIBIWU_zLlrVS8Z1lZiHxx-vLf9MKTnYSxpbajyaWDiZBlVueFrfpJTJ_Yjnrz5DJlcH0q7Awb5qmwkKq6JLZZYB1m7ygeliySdCj4IV5SEbtSANoG6FY9t9uyoa5nfE9yM2T17nCgWINjQ7HLHEE-ucD8_sHX6cDoXxAEys4vscxpGoHp5J3TWodGFa7bUzkgbTNjuxS1cqEcNUIuat4wrc_-n4PNC2UZQqEOI0P7qlbYgRcekMxjzd33KyA0aGOSZK7g0QW2Sk9sxuclNMAABmUBpflH1WCvbgD5rCCwoPktmJfdf84-VqG7oUOII19iBDKTeZVTcsgTywA9D95ubBgLgj1sHYSpnIqlLgb1ZceYcRQstMcZO7rKuxMTn6sB8XTyWz3arRiQ_aol3BraP0Yqvwhi-Uw/4gg/qJPEh7mETPGkAN8R1O3XSQ/h0/h001.A8nv2bIwa1tPvRmcd5IsNvOKIR5iTzVWWbHtajDkbvU"><span class="translation_missing" title="translation missing: en.templates.posts.email.v3.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;"> Absolute Zero: Reinforced Self-play Reasoning with Zero Data </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 Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction and RM-R1: Reward Modeling as Reasoning </p></td></tr></table></td></tr><tr><td style="height:0px;width:0px;"><div style="height:1px;" data-open-tracking="true"> <img src="https://elink4f7.mail.bycloud.ai/ss/o/u001.3wmUuY8gEWd4_869a_eXcg/4gg/qJPEh7mETPGkAN8R1O3XSQ/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 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>May 5th ~ May 11th</i><br><i>#55 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;">♥ 1.5k</span></span> <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.DUiN96-Eq7pUHzwEhy5j28ouWJyvSdmf8_Wq6ARo02ra6MwosMBElshjGHp6vTod1t7XEFBBFJkT4yUqC2tEkZkw2Rn0v0VwqxLJCit3NMWm4GneNiPSsdJErafTdzTFm9FpZDJuenOhmq9Lcubb0NWZz5-AI1UEq-pUxgJxAHuAPR4CiisyX3sBQ1M7Y3nE/4gg/qJPEh7mETPGkAN8R1O3XSQ/h1/h001.AxzzPFbZ2hTyvRxOJqLtcJwbOsFBfuAXtV6KZRIQhtA" target="_blank" rel="noopener noreferrer nofollow"><span>Prime Intellect has launched INTELLECT-2</span></a>, which is the first 32B parameter model trained using fully asynchronous reinforcement learning across a decentralized network of permissionless compute contributors. </p><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:480px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/7ba71c7c-5951-4052-a01d-6a08ad9d90e7/68210770ed19e45df800ade8_Screenshot_2025-03-25_at_17.46.32__2_.png?t=1747158565" alt="" height="auto" width="480" 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;">♥ 434</span></span> <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.VomAAYwkCjux8i_FMc4kJQlOfcZZWR8Cul1IbM_irVcJB_FdEYd2j_i6gapUYsr0w6JypaBnU4ZHZ0Pkm5whFt-TYSzZawaMct0-AGUnzzMrS3NGRwG8oBv2NTXyzZtopOmRWoOwXu55UKsnq_Vto1w5IS0DcWJBfVWw9ZQHj8BWNrnD2QHa4djUZabbvs6V/4gg/qJPEh7mETPGkAN8R1O3XSQ/h2/h001.j4aNC6LIdd_Mwplu-wuOgB7-oHlrhBc1Et4053jTVkY" target="_blank" rel="noopener noreferrer nofollow"><span>ByteDance has released Seed1.5-VL technical report</span></a>, a new vision-language foundation model that integrates a 532M-parameter vision encoder with a 20B active parameter Mixture-of-Experts LLM architecture. Despite its relatively compact design, the model achieves <b>state-of-the-art performance on 38 out of 60 public benchmarks</b>. It also demonstrates exceptional capabilities in agent-centric tasks like GUI control and gameplay, outperforming established systems such as OpenAI CUA and Claude 3.7. </p><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:540px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/237c6d57-e0a6-453d-85d4-16cb853e082a/Screenshot_2025-05-13_140441.png?t=1747159493" alt="" height="auto" width="540" 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;">♥ 4.7k</span></span> <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.c6q0w4g5sodbtO4I1B_pxU6myLBNr0kxu76gma1gUlbxfed0QyLx1t7Tz2zGhQqcM-YyuZoi252_B9hGfzkR95KRrKHtGXRBsGfXWY8rea6CGJzuykZB71_zq-L1wUaJlzmsN65h-FMkdnabJKNDKV7ULOYC920-ae_p4xQ9cIA/4gg/qJPEh7mETPGkAN8R1O3XSQ/h3/h001.DUvCjBzRbfFXfbgh3o1UHJx3MdhsSmrfiNFKu0r4c9c" target="_blank" rel="noopener noreferrer nofollow"><span>Mistral AI has launched Mistral Medium 3</span></a>, a new language model that delivers state-of-the-art performance at <b>8X lower cost</b>. The model performs at or above <b>90% of Claude Sonnet 3.7</b> across benchmarks at a significantly reduced price point ($0.4 input / $2 output per million tokens) and outperforms open models like Llama 4 Maverick particularly in professional use cases such as coding and multimodal understanding. You can use it on <a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.c6q0w4g5sodbtO4I1B_pxfKZ3gkFe-vyD9nGy-jO20sY_8xI0McHM20x_w-1fmX94MpLiDaCQNh_heVX3u3MxLj7mKHwe6joOd8DczlebBCdDGO-5XR-b-kKvwGWaCngnS34BZYUcO_AGjoRtv2XGiJ_OSv4lww8jHhnKLeoFgc/4gg/qJPEh7mETPGkAN8R1O3XSQ/h4/h001.g62EV7guZwaZB8BupAFDtaRcgPNodT8LvBNkYUPIJTs" target="_blank" rel="noopener noreferrer nofollow"><span>Mistral La Plateforme</span></a> and Amazon Sagemaker. </p><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:480px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/83e2bc20-680f-48e5-8d3e-ccba0fd04116/table-medium-6.png?t=1747159195" alt="" height="auto" width="480" 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><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-color:#2C81E5;border-style:solid;border-width:5px;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><tr><td class="dd" align="center" valign="top" style="color:#2A2A2A;font-weight:Bold;padding:0px 28px;text-align:center;"><h2 style="color:#2A2A2A;font-weight:Bold;mso-line-height-alt:150.0%;"><span style=""><a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.oB7zuO_W-X4Toa45C28ng-igpo6AcUtZbSyZW89O-Mas9ZhHBoB-ejMBkpv835MJk-EggXtrrfOL6PMrNu3UdLk_ZOMOaTTwDQ_P_Za4K8t7vrIO85sac5Pr0lh7sWiI/4gg/qJPEh7mETPGkAN8R1O3XSQ/h5/h001.dD2mpkjrCJLLx30vrREYtYN_MDzbVWHKJq1LXWDiSpE" target="_blank" rel="noopener noreferrer nofollow"><span>Bhindi</span></a></span><span style=""> is your cursor for apps</span></h2></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/ea75eab3-bda3-4685-8399-71aea5a36b81/2.gif?t=1746820560" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.oB7zuO_W-X4Toa45C28ng-igpo6AcUtZbSyZW89O-Mas9ZhHBoB-ejMBkpv835MJ63tKPLPzEFXj2VmV_W3SYsf5saQA8FMpV9zAAHhZ3RtNctOiA8XVl5WFziPct8eY/4gg/qJPEh7mETPGkAN8R1O3XSQ/h6/h001.zfrE1hhp9ijC2GQDpET-PkCU0tSpK4ibZQrQgixNyMc" target="_blank" rel="noopener noreferrer nofollow" style="text-decoration:underline;text-decoration-color:#000000;"><p><span style="">Bhindi in action</span></p></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%;"><span style="">It’s your AI tool, connecting 70+ tools to spin up seamless workflows in seconds.</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="">Tell Bhindi what you need, and it’ll stitch together your apps like magic. You can use Bhindi to:</span></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"><ul style="font-weight:normal;list-style-type:disc;margin-bottom:12px !important;margin-top:12px !important;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="">Pull tasks from Trello, merge the right PRs on GitHub, and drop updates in Slack.</span></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="">Search products on Amazon, log them in Google Sheets, and notify the team — one simple query.</span></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="">Quote a tweet, set calendar reminders, plan trips, hunt jobs — no tab juggling.</span></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="">Bhindi can fetch your last emails, highlights the latest one about leave, and keeps your records updated.</span></p></li></ul></div></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="">We’ve got image generation and TTS support across models too.</span></p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.oB7zuO_W-X4Toa45C28ng-igpo6AcUtZbSyZW89O-Mas9ZhHBoB-ejMBkpv835MJf7BWgUQxazAviUAgRW_RVvRc-Pj-1hozjgsUpkQVR2EGIjpkruzD8aL5uQWIp4Vm/4gg/qJPEh7mETPGkAN8R1O3XSQ/h7/h001.87FFp5S0Vr42qfynGVuI8zw9JXJbzsk47Z1Vm962gHY" 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/066dd578-2d7f-44ac-9b38-f975905425f1/image__2_.png?t=1746820552" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></a></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.oB7zuO_W-X4Toa45C28ng-igpo6AcUtZbSyZW89O-Mas9ZhHBoB-ejMBkpv835MJJdVTgMeIYe3a4MGC3yh8_LgI8AchRVHmRXSZdfCaVuXepSC-qb68A0xz4EgqlWK2/4gg/qJPEh7mETPGkAN8R1O3XSQ/h8/h001.KqBYrBhnREaG1Ypz8nklmwccFfqwg5i8WN6JDsMH28s" target="_blank" rel="noopener noreferrer nofollow" style="text-decoration:underline;text-decoration-color:#000000;"><p><span style="">Connect any apps for Bhindi to automate for you</span></p></a></td></tr></table></td></tr><tr><td class="dd" align="center" style="padding:0px 28px;text-align:center;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style=""><b>The new UI is a conversation.</b></span></p></td></tr><tr><td class="dd" align="center" style="padding:0px 28px;text-align:center;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style="">Just tell your requirements in plain English and Bhindi will handle the rest.</span></p></td></tr><tr><td class="dd" align="center" style="padding:0px 28px;text-align:center;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style=""><b>Give it a spin. We’d love your feedback!</b></span></p></td></tr><tr><td align="center" 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 role="none" border="0" cellspacing="0" cellpadding="0" align="center" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle" height="44.75" style="height:44.75px;background-color:#2C81E5;border-color:#DFD150;border-radius:10px 10px 10px 10px;border-style:solid;border-width:0px 0px 0px 0px;color:#FFFFFF;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.oB7zuO_W-X4Toa45C28ng-igpo6AcUtZbSyZW89O-Mas9ZhHBoB-ejMBkpv835MJ4-y26vhxNo7GAG6g2x49imU_7Oug1lF9VGHXtAPXd8meF4WRAMzh7bQV8czHlAmu/4gg/qJPEh7mETPGkAN8R1O3XSQ/h9/h001.m9ELQAVaYrggL7qb6LHDlF-H1eY3Sg38P-lC7PGAOuc" target="_blank" rel="noopener noreferrer nofollow" style="color:#FFFFFF;display:block;font-size:16px;font-size:16px;font-weight:normal;padding:0px 14px;padding:14px 14px 14px 14px;text-decoration:none;"> Check Out Bhindi.io </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%;"><span style=""><a class="link" href="https://elink4f7.mail.bycloud.ai/ss/c/u001.tLfGW26lAwaS9gFg17HSoGymQ3NNPtd5dE5MV_8UgjIDFPVXngz8pvQBldSW42yhUe_Qiq6DgEPMEBuPL9yfRpXelTiuu2kS8pLFvsoem_XoZoy_n13sTKUhZIbl0VH6/4gg/qJPEh7mETPGkAN8R1O3XSQ/h10/h001.m0zToGtz-7igbhEzRmExxnabk0ZJd71gXn8nq0xl3JE" target="_blank" rel="noopener noreferrer nofollow"><span>Advertise with Us</span></a></span></p></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="absolute-zero-reinforced-selfplay-r" 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%;">Absolute Zero: Reinforced Self-play Reasoning with Zero Data</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%;"><span style=""><i>Zhao et al. [Tsinghua University, Beijing Institute for General Artificial Intelligence, Pennsylvania State University]</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;"> ♥ 1.6k </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></p></td></tr><tr><td align="center" valign="top" class="dd"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.fUNb4GdFo9D3F8WuLArtoS8XJu_9lclh0930dNvK7_pojTopAkYEizn4FWh86cGFd86-5E6sHhnGI-7CtW64V9wRsFF9lJH1c_rlxxvuy4AmzWj4yMIJwahWev-Uo-oVeZjeYeT8OcqdkcAwmWrZag/4gg/qJPEh7mETPGkAN8R1O3XSQ/h11/h001.-nyPii6gEvqB9Ju131olafgpL_k31iRPgzx40UzgXyo" style="text-decoration:none;" target="_blank"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center" style="margin-bottom:12px;margin-top:12px;padding-left:12px;padding-right:12px;"><tr><td align="center" valign="top" class="o" style="padding:12px 12px 12px 12px;;background-color:#FFFFFF;border-color:#F1F1F1;border-radius:5px 5px 5px 5px;border-width:1px 1px 1px 1px;"><table role="none" border="0" cellspacing="0" cellpadding="0" align="right" width="100%"><tr><!--[if mso]><td width="0"><table cellpadding="0" cellspacing="0" border="0" role="presentation" style="display:none;"><tr><![endif]--><td class="embed-img mob-stack" align="center" valign="top" style="width:35%;min-height:100px;vertical-align:middle;display:none;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.fUNb4GdFo9D3F8WuLArtoS8XJu_9lclh0930dNvK7_pojTopAkYEizn4FWh86cGFd86-5E6sHhnGI-7CtW64V37lxt-H3YQmdApLcfc18-tWovLGd9rShujLY64pIO_PbCzoWOZKhwGC9paBSQyzsQ/4gg/qJPEh7mETPGkAN8R1O3XSQ/h12/h001.ZxYNx46WvLSADap3ybKH3RMFS53tdTZmcCmdmPivj-8" style="text-decoration:none;" target="_blank"><img src="" width="100%" style="display:block;"/></a></td><!--[if mso]></tr></table></td><![endif]--></tr><tr><td align="center" valign="top" class="cc"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="left" valign="top" class="l"><p>Absolute Zero Reasoner</p></td></tr><tr><td align="left" valign="bottom" class="n" style="vertical-align:bottom;padding-top:12px;"><p style="word-break:break-word;">andrewzh112.github.io/absolute-zero-reasoner</p></td></tr></table></td><!--[if mso]><td width="0"><table cellpadding="0" cellspacing="0" border="0" role="presentation" style="display:none;"><tr><![endif]--><td class="mob-hide" align="center" valign="top" style="width:35%;min-height:100px;padding:0px 0px 0px 12px;vertical-align:middle;"><img src="" width="100%" style="display:block;"/></td><!--[if mso]></tr></table></td><![endif]--></tr></table></td></tr></table></a></td></tr><tr><td id="how-ai-models-can-teach-themselves-" 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%;"><span style="color:rgb(67, 67, 67);">How AI Models Can Teach Themselves Without Human Data</span></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 getting better at reasoning by learning from human-curated examples, but this reliance on expert-crafted data is becoming a bottleneck. As models grow more capable, the effort to maintain high-quality training datasets is getting unsustainable. </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 a new approach called <span style="font-weight:700;"><i><b>Absolute Zero Reasoner (AZR)</b></i></span> that offers a way for models to autonomously evolve their reasoning skills,<b> no human input required</b>. Most reasoning models today depend on reinforcement learning with verifiable rewards (RLVR), where feedback comes from outcome-based metrics like code correctness. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/c2d5d2a0-e9ee-4e09-b4ed-41103c4ee3e1/azr.png?t=1747154298" alt="" height="auto" width="600" 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%;"> Although this method is effective, these methods still need carefully designed question-answer pairs curated by humans. This creates a scalability wall: as tasks grow more complex, manual dataset creation becomes impractical. Worse, if AI eventually outperforms humans, it could stagnate when limited to human-designed challenges. AZR tackles this by eliminating external data entirely. Instead of relying on predefined tasks, the model invents its own problems, solves them, and learns from the results. </p></td></tr><tr><td id="how-absolute-zero-reasoner-works" 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%;"><span style="color:rgb(67, 67, 67);">How Absolute Zero Reasoner Works</span></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 AZR model uses a continuous loop of task creation and problem-solving, guided by three core reasoning modes. It relies on a code executor, which validates tasks and checks solutions and provides objective feedback without human intervention. </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;"><span style="font-weight:700;"><b>Dual Roles: Proposer and Solver</b></span> The same model wears two hats. As a <span style=""><i>proposer</i></span>, it generates coding tasks, like writing a function or predicting an output, while ensuring they’re neither too easy nor unsolvable. As a <span style=""><i>solver</i></span>, it attempts these tasks, refining its reasoning skills through trial and error. Rewards are split: the proposer earns points for creating "Goldilocks" tasks (moderately challenging), while the solver is graded on correctness. </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="font-weight:700;"><b>Three Modes of Reasoning</b></span><br>Tasks fall into three categories, inspired by logical reasoning: </p><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="font-weight:700;"><b>Deduction</b></span>: Predict an output given code and input (e.g., "What does <span style="color:rgb(24, 128, 56);">f(x)=x+2</span> return for <span style="color:rgb(24, 128, 56);">x=3</span>?"). </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="font-weight:700;"><b>Abduction</b></span>: Infer an input that produces a specific output (e.g., "Find <span style="color:rgb(24, 128, 56);">x</span> so that <span style="color:rgb(24, 128, 56);">f(x)=5</span>"). </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="font-weight:700;"><b>Induction</b></span>: Write code that matches input-output examples (e.g., "Create a function that maps these pairs"). </p></li></ol></li></ol></div></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/2f763fbc-3a9e-4e4b-b60a-4403992148e9/image.png?t=1747154446" alt="" height="auto" width="600" 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%;"> Each mode targets different cognitive skills, from step-by-step logic (deduction) to creative problem-solving (abduction). By cycling through these tasks, AZR builds a broad, flexible understanding of code and logic. </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="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;"><span style="font-weight:700;"><b>Code as a Grounded Playground</b></span><br>Using Python as its environment, AZR validates tasks through execution. For example, if the model proposes a function, the code executor runs it to confirm it works. This ensures rewards are based on objective, verifiable outcomes, avoiding the pitfalls of learned reward models that can be "hacked" by exploiting biases. </p></li></ol></div></td></tr><tr><td id="strengths-of-absolute-zero-reasoner" 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%;"><span style="color:rgb(67, 67, 67);">Strengths of Absolute Zero Reasoner</span></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 Absolute Zero Reasoner model was trained entirely without human data and it matches or outperforms models fine-tuned on thousands of expert examples. On coding benchmarks like HumanEval+ and MBPP+, it sets <span style="font-weight:700;"><b>new state-of-the-art scores</b></span>. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/8bd43eca-0fac-428a-8dc9-e0a2414901c1/image.png?t=1747154484" alt="" height="auto" width="600" 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%;"> In math reasoning (AIME, AMC), it shows strong cross-domain generalization, even though it was trained solely on code tasks. Key findings include: </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"><ul style="font-weight:normal;list-style-type:disc;margin-bottom:12px !important;margin-top:12px !important;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="font-weight:700;"><b>Scaling Benefits</b></span>: Larger base models (7B→14B parameters) show bigger performance jumps which suggests continued gains as models grow. </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="font-weight:700;"><b>Code Supercharges Reasoning</b></span>: Models pretrained on code outperformed general-purpose counterparts in math after AZR training, hinting at synergies between programming and abstract reasoning. </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="font-weight:700;"><b>Emergent Planning</b></span>: Like humans, AZR began adding step-by-step comments to its code, mirroring techniques like ReAct prompting, a behavior not explicitly taught. </p></li></ul></div></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/24285270-2e4a-4556-b991-baefc7e13aec/azr_teaser.jpg?t=1747154232" alt="" height="auto" width="600" 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%;"> However, there are caveats. Larger models occasionally produced poor results in reasoning chains, underscoring the need for safety safeguards. Moreover, autonomous systems might develop unintended behaviors, and verifying their solutions grows harder as tasks become more abstract. </p></td></tr><tr><td align="center" valign="top" class="dd"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.CxDkkVpJsBdVoe83c_tBWno2StfHgkdXyV9QnRyXhktsb9F3PAP6chT8ISlmK3CleE-nrNbuKLDjd1QaEQYfEJ4sJ6FnSi4oa2tqlRnk7pHIBBDU5Q8jA0j5LWuNJtWvFMkWtPpt7Yb5sm93By8RGDpOghln3pqKhwFdnFyd6hNZi31P7BtXYw5IMWsKIdHmw0aVz8oNJ1RxYLgbdNVzPQ/4gg/qJPEh7mETPGkAN8R1O3XSQ/h13/h001.TVxADZ05riPLbmZ2Q0HTqJ0nyv1BTSYL8yBNgyuMPNM" style="text-decoration:none;" target="_blank"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center" style="margin-bottom:12px;margin-top:12px;padding-left:12px;padding-right:12px;"><tr><td align="center" valign="top" class="o" style="padding:12px 12px 12px 12px;;background-color:#FFFFFF;border-color:#F1F1F1;border-radius:5px 5px 5px 5px;border-width:1px 1px 1px 1px;"><table role="none" border="0" cellspacing="0" cellpadding="0" align="right" width="100%"><tr><!--[if mso]><td width="0"><table cellpadding="0" cellspacing="0" border="0" role="presentation" style="display:none;"><tr><![endif]--><td class="embed-img mob-stack" align="center" valign="top" style="width:35%;min-height:100px;vertical-align:middle;display:none;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.CxDkkVpJsBdVoe83c_tBWno2StfHgkdXyV9QnRyXhktsb9F3PAP6chT8ISlmK3CleE-nrNbuKLDjd1QaEQYfEJ4sJ6FnSi4oa2tqlRnk7pHIBBDU5Q8jA0j5LWuNJtWvjKBQu2Z-Ksd4TpKLEfg4ZXTx9uNaBQkLwR-3u71wGlJmBIm5R6wmnrftmNiTSqy2MBzjxLvRk5bsSWNHbdRZ1Q/4gg/qJPEh7mETPGkAN8R1O3XSQ/h14/h001.NzCmft3e-CQKAQcj6_brg-LiglbkHJiRiE7-2c9bzHw" style="text-decoration:none;" target="_blank"><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/collections/andrewzh/absolute-zero-reasoner-68139b2bca82afb00bc69e5b.png" width="100%" style="display:block;"/></a></td><!--[if mso]></tr></table></td><![endif]--></tr><tr><td align="center" valign="top" class="cc"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="left" valign="top" class="l"><p>Absolute Zero Reasoner - a andrewzh Collection</p></td></tr><tr><td align="left" valign="top" class="m"><p>We’re on a journey to advance and democratize artificial intelligence through open source and open science.</p></td></tr><tr><td align="left" valign="bottom" class="n" style="vertical-align:bottom;padding-top:12px;"><p style="word-break:break-word;">huggingface.co/collections/andrewzh/absolute-zero-reasoner-68139b2bca82afb00bc69e5b</p></td></tr></table></td><!--[if mso]><td width="0"><table cellpadding="0" cellspacing="0" border="0" role="presentation" style="display:none;"><tr><![endif]--><td class="mob-hide" align="center" valign="top" style="width:35%;min-height:100px;padding:0px 0px 0px 12px;vertical-align:middle;"><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/collections/andrewzh/absolute-zero-reasoner-68139b2bca82afb00bc69e5b.png" width="100%" style="display:block;"/></td><!--[if mso]></tr></table></td><![endif]--></tr></table></td></tr></table></a></td></tr><tr><td align="center" 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 role="none" border="0" cellspacing="0" cellpadding="0" align="center" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle" height="44.75" style="height:44.75px;background-color:#2C81E5;border-color:#DFD150;border-radius:10px 10px 10px 10px;border-style:solid;border-width:0px 0px 0px 0px;color:#FFFFFF;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.DUiN96-Eq7pUHzwEhy5j28yjf9KIXZdsXoh1WlHvvKmRsMEIY6ZgXOggmp5tmQToH5CTEKk2gg0c_TX1DJMZJlc33kN1Um2W6MWl0nKVYPxnqGt0PJ4OaYdTOy570nSZ/4gg/qJPEh7mETPGkAN8R1O3XSQ/h15/h001.xHO7wLwyy_XvDeILUkb209JHTFTHDFLEQXJucrBJuXE" target="_blank" rel="noopener noreferrer nofollow" style="color:#FFFFFF;display:block;font-size:16px;font-size:16px;font-weight:normal;padding:0px 14px;padding:14px 14px 14px 14px;text-decoration:none;"> Read Full Paper </a></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="ming-lite-uni-advancements-in-unifi" 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%;">Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction</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%;"><span style=""><i>Gong et al. [Inclusion AI, Ant Group]</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;">♥ 55 </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;"> Multi-modal Architecture </span></span><span style="color:rgb(44, 129, 229);font-size:0.6rem;"> </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 align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/6dfd3ac2-7078-47bb-8412-33ec3105a8c3/Ming_unify_usecases.png?t=1747153883" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>The output results and multimodal interactive demos of Ming-Lite-Uni.</p></td></tr></table></td></tr><tr><td id="understanding-unified-multimodal-mo" 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%;"><span style="color:rgb(67, 67, 67);">Understanding Unified Multimodal Models with Ming-Lite-Uni</span></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%;"> When we think of AI, most people imagine a single system that can understand <span style=""><i>and</i></span> generate images, text, and other modalities. While models like GPT-4o have shown impressive native image generation, many open-source frameworks struggle with a critical problem: balancing high-fidelity visual synthesis with precise semantic understanding. </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%;"> Existing models often prioritize pixel-perfect image generation but this usually results in poor quality context alignment. These images look great but they often miss the intent of the user. This paper introduces <span style="font-weight:700;"><b>Ming-Lite-Uni</b></span>, an open-source multimodal framework designed to unify visual and language tasks without compromising either capability. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/8a19a9d7-7725-4237-8aeb-c5a3b3b4b438/439513082-927e090e-7cda-4f32-81de-774466973077.png?t=1747153897" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td id="how-ming-lite-uni-understands-multi" 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%;"><span style="color:rgb(67, 67, 67);">How Ming-Lite-Uni Understands Multiple Modalities</span></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 Ming-Lite-Uni model uses both frozen and trainable components. The model fixes a pre-trained multimodal large language model (MLLM) to retain its understanding of text and images, while fine-tuning a diffusion model to handle generation. This separation avoids the common pitfall of feature mismatch, where visual synthesis drifts away from the original semantic context. To bridge these components, the team introduced <span style="font-weight:700;"><b>multi-scale learnable tokens</b></span> which uses adaptive query tokens that capture visual details at different resolutions. Low-resolution tokens handle global layout and color, medium ones focus on objects, and high-resolution tokens encode fine textures. These tokens act as a universal language between understanding and generation, ensuring the diffusion model stays aligned with the MLLM’s intent. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/60679498-bcb2-414a-a27c-5a278ea9848d/image.png?t=1747153995" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>The AR part of Ming-Lite-Uni.</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%;"> In addition to this, it also uses the <span style="font-weight:700;"><b>multi-scale representation alignment strategy</b></span>, which enforces consistency across hierarchical features. By aligning intermediate outputs of the diffusion model with the final semantic representations from the MLLM, Ming-Lite-Uni reduces discrepancies that typically plague unified models. This approach improves high-resolution reconstruction quality by over 2 dB in PSNR and boosts generation accuracy. The diffusion model itself is trained with a FlowMatching loss, borrowed from recent advances in continuous trajectory modeling, which helps refine details without destabilizing the frozen MLLM. </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 framework’s architecture also introduces a new multimodal autoregressive module. Instead of reinventing the wheel, it reuses components from existing models like M2-omni and Llama3, modifying positional encodings to handle mixed modalities. This allows Ming-Lite-Uni to process arbitrary-resolution images and variable-length text in a single sequence. This makes it adaptable to tasks from style transfer to multi-round image editing. By freezing the MLLM and focusing training on the diffusion model, the team sidestepped the computational cost of end-to-end optimization while still achieving strong interoperability. </p></td></tr><tr><td align="center" valign="top" style="padding:14px 32px 14px 32px;" class="dd"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.VomAAYwkCjux8i_FMc4kJaoaRcPhi6oj0LL4dkZdoHT9NR9IR0CJsOGWf_IN2CLMGB30TdlBJ9zJ5kNbg4XUR05KXPMO7f_VW_Blj6xjw0XNXv6sP2MOurWpQuSNMFwwkedoa0RKgAgWl0Xh48Hd4w/4gg/qJPEh7mETPGkAN8R1O3XSQ/h16/h001.LCBblpep5cne6HI6R4XjJsDza__oH8ssVqR4FajAr_g" style="text-decoration:none;" target="_blank"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center" style="margin-bottom:12px;margin-top:12px;padding-left:12px;padding-right:12px;"><tr><td align="center" valign="top" class="o" style="padding:12px 12px 12px 12px;;background-color:#FFFFFF;border-color:#F1F1F1;border-radius:5px 5px 5px 5px;border-width:1px 1px 1px 1px;"><table role="none" border="0" cellspacing="0" cellpadding="0" align="right" width="100%"><tr><!--[if mso]><td width="0"><table cellpadding="0" cellspacing="0" border="0" role="presentation" style="display:none;"><tr><![endif]--><td class="embed-img" align="center" valign="top" style="width:100%;min-height:100px;vertical-align:middle;padding:0px 0px 12px 0px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.VomAAYwkCjux8i_FMc4kJaoaRcPhi6oj0LL4dkZdoHT9NR9IR0CJsOGWf_IN2CLMGB30TdlBJ9zJ5kNbg4XUR4lQZRLjjkuQSvUjuFd-Gj-3k8s-W0sIHRbo60HeJ-eQiF4vEniDPh93r_o8Bh92pg/4gg/qJPEh7mETPGkAN8R1O3XSQ/h17/h001.dUBS560P8zLTkv1_bI9ny1O6Xk6aUIyfvAG-Ipj3yKg" style="text-decoration:none;" target="_blank"><img src="https://opengraph.githubassets.com/2fefc469a084f7b8ead176056b1bb80defc5ddba143f974ad5bff1f61805eb45/inclusionAI/Ming" width="100%" style="display:block;"/></a></td><!--[if mso]></tr></table></td><![endif]--></tr><tr><td align="center" valign="top" class="cc"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="left" valign="top" class="l"><p>Ming/Ming-unify at main · inclusionAI/Ming</p></td></tr><tr><td align="left" valign="top" class="m"><p>Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM. - inclusionAI/Ming</p></td></tr><tr><td align="left" valign="bottom" class="n" style="vertical-align:bottom;padding-top:12px;"><p style="word-break:break-word;">github.com/inclusionAI/Ming/tree/main/Ming-unify</p></td></tr></table></td></tr></table></td></tr></table></a></td></tr><tr><td id="performance-and-open-challenges-of-" 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%;"><span style="color:rgb(67, 67, 67);">Performance and Open Challenges of Ming-Lite-Uni</span></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 Ming-Lite-Uni shows promising results. On GenEval (a benchmark for text-to-image generation) it scored 0.62 accuracy which matches specialized diffusion models like SDXL (0.55) and approaching closed-source tools like DALL-E 3 (0.67). In multimodal understanding tasks, it <span style="font-weight:700;"><b>outperformed similarly sized models</b></span> on benchmarks like MMB and MMMU, though it lags behind larger closed-source systems like GPT-4o. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/acbfea60-de6f-4d1b-a093-c735dd0f5486/image.png?t=1747154051" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>Evaluation of text-to-image generation ability on GenEval benchmark Ghosh et al. (2024).</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%;"> However, the framework is still in its alpha stage. It has a few limitations such as a reliance on curated datasets for style transfer and editing, which may restrict generalization. The team also pointed out that scaling the autoregressive component could further close the gap with proprietary models. Future work will focus on expanding the training data and refining the balance between modalities. </p></td></tr><tr><td align="center" 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 role="none" border="0" cellspacing="0" cellpadding="0" align="center" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle" height="44.75" style="height:44.75px;background-color:#2C81E5;border-color:#DFD150;border-radius:10px 10px 10px 10px;border-style:solid;border-width:0px 0px 0px 0px;color:#FFFFFF;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.DUiN96-Eq7pUHzwEhy5j28yjf9KIXZdsXoh1WlHvvKk124PVxHaPBqWIy-XL7p7R9Wr46j0YP3Cglh5tBqAUsrXp4HV1jZupsrpajKgit63SzdnJdx2qFxFgi9p6KpwV/4gg/qJPEh7mETPGkAN8R1O3XSQ/h18/h001.9hMgbGEwJ5gejYGI18rOfuegtxOvrFZFJEpol1bbXkQ" target="_blank" rel="noopener noreferrer nofollow" style="color:#FFFFFF;display:block;font-size:16px;font-size:16px;font-weight:normal;padding:0px 14px;padding:14px 14px 14px 14px;text-decoration:none;"> Read Full Paper </a></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="rmr-1-reward-modeling-as-reasoning" 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%;">RM-R1: Reward Modeling as 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>Chen et al. [University of Illinois Urbana-Champaign, University of California, Texas A&M University]</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;">♥ 184 </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 Reward Modeling </span></span></p></td></tr><tr><td id="how-reasoning-reward-models-are-sha" 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%;"><span style="color:rgb(67, 67, 67);">How Reasoning Reward Models Are Shaping AI Alignment</span></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%;"> When we train any AI model, we use a reward function that tells LLMs what behaviors humans actually want. But today’s reward models have a critical limitation: they’re either too opaque to trust or too simplistic to handle nuanced tasks. Traditional reward models fall into two camps. </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"><ul style="font-weight:normal;list-style-type:disc;margin-bottom:12px !important;margin-top:12px !important;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;"> Scalar models spit out numerical scores without explanation, this leaves users guessing why one response is better than another. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> Generative models produce free-form judgments but often default to surface-level critiques. For example, they will point out grammar errors while missing deeper issues like emotional harm. This lack of interpretability and depth becomes a liability in high-stakes scenarios, for instance, when evaluating mental health advice or complex code. </p></li></ul></div></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/af41c744-34c1-4131-b014-39f1d95a5a10/image.png?t=1747153656" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>The off-the-shelf instruct model overfits to patterns in supervised data, failing to evaluate the emotional harm and lack of nuance in the rejected response.</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%;"> This paper introduces <span style="font-weight:700;"><b>Reasoning Reward Models (REASRMS)</b></span>, a new approach that treats reward modeling not as a black-box scoring game, but as a reasoning-intensive task. The RM-R1 project tackles the above problems by asking: <span style=""><i>What if reward models reasoned like humans?</i></span></p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/2f095e2c-f49d-4011-875c-9b83b6370ba8/rm-r1-1.png?t=1747153581" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>Training pipeline of RM-R1</p></td></tr></table></td></tr><tr><td id="how-reasrms-work-teaching-models-to" 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%;"><span style="color:rgb(67, 67, 67);">How REASRMS Work: Teaching Models to Think Before Judging</span></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%;"> REASRMS uses a two-stage training pipeline that is designed to bake reasoning into every judgment. </p></td></tr><tr><td id="stage-1-distilling-high-quality-rea" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h4 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:112.5%;"><span style="color:rgb(102, 102, 102);font-weight:700;"><b>Stage 1: Distilling High-Quality Reasoning</b></span></h4></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 starts with a standard instruction-tuned LLM (like Qwen-2.5-14B), the team first teaches it to generate structured critiques. After this, they create “reasoning traces” using synthetic data from stronger models (e.g., Claude-3). These are detailed evaluations where the model explains its rubric (e.g., “Does this response validate emotions?”) before declaring a winner. This phase helps the model internalize <span style=""><i>how</i></span> to evaluate, not just <span style=""><i>what</i></span> to choose. </p></td></tr><tr><td id="stage-2-reinforcement-learning-with" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h4 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:112.5%;"><span style="color:rgb(102, 102, 102);font-weight:700;"><b>Stage 2: Reinforcement Learning with Verifiable Rewards</b></span></h4></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%;"> However, distillation alone risks overfitting to synthetic patterns. To refine the model’s judgment, reinforcement learning (via <span style="font-weight:700;"><b>Group Relative Policy Optimization</b></span>) rewards the model for correct final verdicts while penalizing deviations from its original knowledge. The reward signal focuses <span style=""><i>only</i></span> on whether the model’s final answer matches human preferences, no partial credit for elegant but incorrect reasoning. This forces the model to align its elaborate critiques with ground-truth outcomes. </p></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/169df21e-61cc-4564-a9c7-e82ef4c9a1cd/image.png?t=1747153736" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>The user prompt used for RM-R1 rollout (for reasoning models).</p></td></tr></table></td></tr><tr><td id="the-chainof-rubrics-framework" class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:normal;padding:0px 28px;text-align:left;"><h4 style="color:#2A2A2A;font-weight:normal;mso-line-height-alt:112.5%;"><span style="color:rgb(102, 102, 102);font-weight:700;"><b>The Chain-of-Rubrics Framework</b></span></h4></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%;"> At inference time, RM-R1 classifies tasks into two types: </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"><ul style="font-weight:normal;list-style-type:disc;margin-bottom:12px !important;margin-top:12px !important;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="font-weight:700;"><b>Chat</b></span>: Generates custom rubrics (e.g., “emotional safety,” “actionable advice”) tailored to the query. </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="font-weight:700;"><b>Reasoning</b></span>: Solves the problem itself first, then compares responses against its own solution. </p></li></ul></div></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 division lets the model apply domain-specific evaluation strategies. For emotional support queries, it might prioritize empathy; for math problems, correctness reigns supreme. </p></td></tr><tr><td align="center" valign="top" style="padding:14px 32px 14px 32px;" class="dd"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.VomAAYwkCjux8i_FMc4kJUA7HM25DlpVvYVqiAsv0GRxgkbLS-Ht0CWf87FtD7lOzaR26wsoJcmnwW7dQ85fR33l60fAZ254AOhKwgSUZ3tfoXn_Kp1M225sPg3UvmG2/4gg/qJPEh7mETPGkAN8R1O3XSQ/h19/h001.52tnb0IQnKP1Zkv3r_DxKjvk4MH4VUhG_ncNXvP_Uq0" style="text-decoration:none;" target="_blank"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center" style="margin-bottom:12px;margin-top:12px;padding-left:12px;padding-right:12px;"><tr><td align="center" valign="top" class="o" style="padding:12px 12px 12px 12px;;background-color:#FFFFFF;border-color:#F1F1F1;border-radius:5px 5px 5px 5px;border-width:1px 1px 1px 1px;"><table role="none" border="0" cellspacing="0" cellpadding="0" align="right" width="100%"><tr><!--[if mso]><td width="0"><table cellpadding="0" cellspacing="0" border="0" role="presentation" style="display:none;"><tr><![endif]--><td class="embed-img" align="center" valign="top" style="width:100%;min-height:100px;vertical-align:middle;padding:0px 0px 12px 0px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.VomAAYwkCjux8i_FMc4kJUA7HM25DlpVvYVqiAsv0GRxgkbLS-Ht0CWf87FtD7lOGqrzJu_tvh2qej64k_QeHuqjLVB-EFTrfJmkE-yB6bOqrPk5hCSXaueiBQF4rjR6/4gg/qJPEh7mETPGkAN8R1O3XSQ/h20/h001.iCy6zV9YMYPvSqd-NT71TwHm6bV3QGv3H6DO_KzkPRA" style="text-decoration:none;" target="_blank"><img src="https://opengraph.githubassets.com/c004c9cb4a7e6295ae4bff8f6f3ae71d0804ebf5ae55d9fc2aa3f89af0345e80/RM-R1-UIUC/RM-R1" width="100%" style="display:block;"/></a></td><!--[if mso]></tr></table></td><![endif]--></tr><tr><td align="center" valign="top" class="cc"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="left" valign="top" class="l"><p>GitHub - RM-R1-UIUC/RM-R1</p></td></tr><tr><td align="left" valign="top" class="m"><p>Contribute to RM-R1-UIUC/RM-R1 development by creating an account on GitHub.</p></td></tr><tr><td align="left" valign="bottom" class="n" style="vertical-align:bottom;padding-top:12px;"><p style="word-break:break-word;">github.com/RM-R1-UIUC/RM-R1</p></td></tr></table></td></tr></table></td></tr></table></a></td></tr><tr><td id="outperforming-big-ll-ms-with-smalle" 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%;"><span style="color:rgb(67, 67, 67);">Outperforming Big LLMs with Smaller, Smarter Models</span></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 model trained using the REASRMS approach described above performed quite well on a number of benchmarks: </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"><ul style="font-weight:normal;list-style-type:disc;margin-bottom:12px !important;margin-top:12px !important;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;"> On <span style="font-weight:700;"><b>RewardBench</b></span>, the 32B variant outperformed GPT-4o and Claude-3 by up to <span style="font-weight:700;"><b>13.8% accuracy</b></span>. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> In <span style="font-weight:700;"><b>RM-Bench</b></span> (a test of sensitivity to subtle errors), it achieved <span style="font-weight:700;"><b>83.9% accuracy</b></span>, 12.8% higher than prior models, particularly shining in math and coding evaluations. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> Even smaller 7B/14B models rivaled or surpassed much larger LLMs, which suggests efficiency gains from focused reasoning training. </p></li></ul></div></td></tr><tr><td align="center" valign="top" style="padding-bottom:20px;padding-left:28px;padding-right:28px;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:600px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/87e0e77f-3397-4470-b44b-6efcdf7775ba/image.png?t=1747153775" alt="" height="auto" width="600" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="center" valign="top" class="t" style="width:600px; padding: 4px 0px 4px 0px;"><p>Results of proposed method and baselines on the RewardBench.</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%;"> While REASRMS excel at structured reasoning, they occasionally overfit to synthetic critique formats. Although larger models performed better, the gains from REASRMS’ training pipeline outstripped raw scaling. The team also notes that current benchmarks underemphasize <span style=""><i>multilingual</i></span> or <span style=""><i>multi-modal</i></span> tasks. </p></td></tr><tr><td align="center" 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 role="none" border="0" cellspacing="0" cellpadding="0" align="center" style="margin:14px auto 14px auto;"><tr><td align="center" valign="middle" height="44.75" style="height:44.75px;background-color:#2C81E5;border-color:#DFD150;border-radius:10px 10px 10px 10px;border-style:solid;border-width:0px 0px 0px 0px;color:#FFFFFF;font-family:'Open Sans','Segoe UI','Apple SD Gothic Neo','Lucida Grande','Lucida Sans Unicode',sans-serif;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.DUiN96-Eq7pUHzwEhy5j28yjf9KIXZdsXoh1WlHvvKmuAb5_DbbWlGeq1xSB7XuSZ940QkPnWmRD7sjG04gXfHm84mONT0FE8uV2eLNe_LLhFcYbNvVsYA3r5vmBEJ0S/4gg/qJPEh7mETPGkAN8R1O3XSQ/h21/h001.41Ldsx-vD9qdtYbIdHm-iiuOQEd-UDI6kKMZCdxMcxA" target="_blank" rel="noopener noreferrer nofollow" style="color:#FFFFFF;display:block;font-size:16px;font-size:16px;font-weight:normal;padding:0px 14px;padding:14px 14px 14px 14px;text-decoration:none;"> Read Full Paper </a></td></tr></table></td></tr><tr><td class="dd" style="padding: 20px;"><table width="100%" cellpadding="0" cellspacing="0" role="none" style="max-width:520px;margin:0 auto;"><tr><td class="q" style="padding:16px 16px 6px 16px;"><a href="https://elink4f7.mail.bycloud.ai/ss/c/u001.tLfGW26lAwaS9gFg17HSoDDFT6eh5Nsg0xYVQj-h6I3o9m2k79_qw4izMYhmcI36hhbCHI80ho-lOD75yIU7vWpxroPeINBXrCmRtusZv5ORpyFKH5Ej7584XO1Co7tnqCI5loPkCt1kJ5WVFIrNphW_uHbVemjLp4SPq4qOEEQ/4gg/qJPEh7mETPGkAN8R1O3XSQ/h22/h001.uTrXsd89vgtK-WRA0vcu6pAMv2aCMeK8FWkPhw2tNzc" style="text-decoration:none !important;"><table width="100%" cellpadding="0" cellspacing="0" border="0" role="none"><tr><td width="100%" style="padding: 0 0 14px 0;text-decoration:none;width:100%;"><table width="100%" cellpadding="0" cellspacing="0" border="0" role="none"><tr><td width="36" style="width:36px;"><img src="https://pbs.twimg.com/profile_images/1698572487909400576/BvncwnrP_normal.jpg" alt="tw profile: The AI Timeline" style="display:block;width:36px;height:36px;border-radius:50%;border:0;"/></td><td width="400" style="padding:0 0 0 8px;text-decoration:none;"><span style="display:block;font-size:14px;color:#1c2022;font-weight:700;"> The AI Timeline </span><span style="display:block;color:#697882;font-size:14px;"> @TheAITimeline </span></td><td width="24" align="right" style="vertical-align:text-top;"><img width="24" height="24" loading="lazy" alt="tw" style="border:0;" src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/static_assets/x_logo.png"/></td></tr></table></td></tr><tr></tr><tr><td style="word-break:break-word;"><p>🚨This week's top AI/ML research papers:</p><p>- Absolute Zero <br>- RM-R1 <br>- Seed-Coder <br>- Flow-GRPO <br>- ZeroSearch <br>- Ming-Lite-Uni <br>- A Survey on Large Multimodal Reasoning Models <br>- On Path to Multimodal Generalist <br>- ZeroSearch <br>- HunyuanCustom <br>- Unified Multimodal CoT Reward Model through</p></td></tr><tr><td style="padding:12px 0 0 0;"></td></tr><tr><td align="center" style="padding:8px 0 0 0;width:480px;"><img src="https://pbs.twimg.com/media/Gqr7qtzXwAAxU37.jpg" width="480" height="auto" style="display:block;border:1px solid #E1E8ED;border-radius:5px;width:100%;max-width:480px;height:auto;"/></td></tr><tr><td height="8" style="line-height:1px;font-size:1px;height:8px;"> </td></tr><tr><td align="left" valign="top" class="s"><p>6:01 PM • May 11, 2025</p></td></tr><tr><td height="10" style="line-height: 1px; font-size: 1px; height: 10px;"> </td></tr><tr><td height="1" bgcolor="#e1e8ed" style="line-height:0px;font-size:0px;height:1px;"></td></tr><tr><td height="10" style="line-height:1px;font-size:1px;height:10px;"> </td></tr><tr><td align="left" valign="top" class="s"><p><b style="color:#1C2022">1.01K</b> Likes <b style="color:#1C2022">121</b> Retweets </p></td></tr><tr><td align="left" valign="top" class="s"><div align="center" style="text-align:center;margin-top:4px;margin-bottom:4px;padding:8px;border:1px solid #ccd6dd;border-radius:9999px;color:#1B95E0"><b>8 Replies</b></div></td></tr></table></a></td></tr></table></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_/4gg/qJPEh7mETPGkAN8R1O3XSQ/h23/h001.xGA1MBViJEVkrPPAGN7pjyWm7pQg4ggLxeJrtFprfuk" 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_zQSVGWJ8AAmPw2en2/4gg/qJPEh7mETPGkAN8R1O3XSQ/h24/h001.DMDujlpgxork9Rb_Hp0t1SC3HYVsaz0wy5q3XlJnE8s" 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-DJgyVFmavJPa0OyKRRnvw4o7XGyvIv7PRofnmX5IxuBgNIJB1ELrnyTTI9ABBDfOCc0RWIIlXiVIUD1cUAjhrIPBVDS8rWH2amTWBxEREUTiKkv9T1GVSViY3WMi5QygjSSTiSvNeml_jKmfWnX_T50EkZkFpqOYFM3cM3TnvCEN6h8wQIvhby7L3s3thY_lNwTvOJifi3Q1zxjJmBmQXHASOzsZhAQ4X_opwpHV-S9mdaVU7V-h-KYwXQQW9UqUZJB9dA0k92Aw67PAVDtZm6k3_ebw16VmXs-tAAuEDwEAZGtRkJ-2rL_jlssalJyMwdeVzaas--s47Udqr_uTwi8N3QMqDA-FizAuximybqiU4tozNIDOKkcdie5j3VhqZhIih_zpPs4OcFJ1afXsBbuWUrcM44A1FBQwpK_uPoSHK72UmYRkl7uw1VtUVjyXnLIDHgWP0R4w3--OADJPHq-7tWrrQh2xuxMH4y1U3jK5Q1BtooCuAGIrrkL7CZOwQAiLWKz3W8o_5S24jZoqJHGDdrPmBqIbLkiFl5Jk2G1eiOZvxwsWmnjUAbFCVq2V5S07ujMsj6oEr9HI0E871TKM93vJknt9LM1YIhfFAUEmELYGvIJKVyvlg4Dw90xVDqBCcCGM3rNGEM3mYHteNf8mEHliODLcb_0IzConLlwl3QgVC2rR-YQxanmhPCYbrSWBS5teQrp311bjIJ-inq2rxsHFaasdZG0ENZmsRJKWaDkMnLERB1_v_7Q/4gg/qJPEh7mETPGkAN8R1O3XSQ/h25/h001.u0-CaiCUQL8XOeH0fC44LoPWLH00KI5XIjmv9FfQv68" 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_OdOKOji4_9sQh0KLRgMC7AQp7C_zXr9PMqPeR7Tj4UOR0MBu8L0ETUL7ZzMVs6RfKBV3nKhcYayf0cTLrty25Eatyi_Rx97yFntzDK7iDeY0Fy60srLu7eEN5ZW9muToQBC9hQXBPyRzkUyzd6XACmmn0balLQqSYTcgr-gMtIJz6k7Jfamapx50vqfBsLmyQWcOr6ebRyWJuRAROY4_xZtzt7e/4gg/qJPEh7mETPGkAN8R1O3XSQ/h26/h001.rsQpiQ3WGEBD_tS2HGIAwlRM_tkLsuFV5c85WX7glkw"><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/4gg/qJPEh7mETPGkAN8R1O3XSQ/h27/h001.7R8xXEs4Ps0vkdwbmOcAWgo_ynmMI6XLu9Umuo8xYcg' 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>