<div dir="ltr"><div><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt">Dear All,</p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">We are excited to announce the </span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">PTA: From Pretrained Representations to Acting Agents</span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"> workshop at </span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">NeurIPS 2026 in </span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">Sydney, Australia</span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">!</span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"> </span>📋<span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap"> We’re calling for submissions!</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">⏰ Paper submission deadline: </span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">Sept 5, 2026 (AoE)</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">🌐 Website: </span><a href="https://ptaworkshop.github.io/" target="_blank" style="text-decoration:none"><span style="font-family:Arial,sans-serif;background-color:transparent;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">https://ptaworkshop.github.io/</span></a></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">📋 Submission link: </span><a href="https://openreview.net/group?id=NeurIPS.cc/2026/Workshop/PTA" target="_blank" style="text-decoration:none"><span style="font-family:Arial,sans-serif;background-color:transparent;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">https://openreview.net/group?id=NeurIPS.cc/2026/Workshop/PTA</span></a></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">Our goal is to explore how to obtain </span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">actionable pretrained representations</span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"> and align them with control agents at </span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">test time</span><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">—bridging pretraining and test-time decision making.</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">Call for Papers:</span></p><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:12pt;margin-bottom:0pt"><span style="background-color:transparent;font-variant:normal;vertical-align:baseline">Specific topics include, but are not limited to:</span></p></li></ul><ol style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="margin-left:36pt;list-style-type:decimal;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-variant:normal;vertical-align:baseline">What makes a pretrained representation actionable?</span></p></li><li dir="ltr" style="margin-left:36pt;list-style-type:decimal;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-variant:normal;vertical-align:baseline">How to align with and use pretrained representations at test time?</span></p></li><li dir="ltr" style="margin-left:36pt;list-style-type:decimal;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-variant:normal;vertical-align:baseline">How to adapt pretrained knowledge to new tasks?</span></p></li><li dir="ltr" style="margin-left:36pt;list-style-type:decimal;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-variant:normal;vertical-align:baseline">How to evaluate actionable representations?</span></p></li><li dir="ltr" style="margin-left:36pt;list-style-type:decimal;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-variant:normal;vertical-align:baseline">What can go wrong when pretrained agents act?</span></p></li></ol><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><span id="m_4937415020668655904gmail-docs-internal-guid-b4332eb1-7fff-4c0a-3a00-1d50fe5e5e1f" style="font-weight:normal"></span></span></p><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(34,34,34);background-color:transparent;font-variant:normal;vertical-align:baseline">We welcome both short papers (4 pages) and long papers (up to 9 pages), formatted using the NeurIPS template and submitted through OpenReview.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(34,34,34);background-color:transparent;font-variant:normal;vertical-align:baseline">All accepted contributions will be presented during the poster sessions.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(34,34,34);background-color:transparent;font-variant:normal;vertical-align:baseline">A select number of submissions will also be invited for contributed talks.</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="color:rgb(34,34,34);background-color:transparent;font-variant:normal;vertical-align:baseline">Submissions are non-archival and may be under review or concurrently submitted elsewhere. We especially encourage ongoing and unpublished work.</span></p></li></ul><div><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap"><br></span></div><div><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">If you are excited about connecting representation learning, RL, planning, and test-time decision making, we hope you’ll join us in Sydney! </span>🦘</div><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">Best regards,</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"><span style="font-family:arial,helvetica,sans-serif;white-space:normal">The Organizing Team</span></span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Ping-Chun Hsieh (NYCU), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Kuang-Huei Lee (Google DeepMind), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Bo Dai (Georgia Tech), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Yen-Ling Kuo (UVA), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Georgia Chalvatzaki (TU Darmstadt), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Karen Leung (UW / NVIDIA), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Co Yong (NTU), </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial,sans-serif;white-space:pre-wrap">Claas Voelcker (UT Austin)</span></p></div><span class="gmail_signature_prefix">-- </span><br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div>Ping-Chun Hsieh (謝秉均)</div><div>Associate Professor</div><div>Department of Computer Science</div><div>National Yang Ming Chiao Tung University</div><div><a href="https://pinghsieh.github.io/" target="_blank">https://pinghsieh.github.io/</a></div></div></div></div><img src="https://email-signature-image.com/signature.gif?u=3802879&e=1233945343&v=764ee3fddb4e61ff6d2749b3e2e0e62afafabc2ac9e6ca71c2f4499a0aa166ef" alt="" width="0" height="0" style="width:2px;max-height:0;overflow:hidden">