<div dir="ltr">Hi all,<div><br></div><div>We are excited to bring a workshop on Interpretability to NeurIPS 2024, called <a href="https://interpretable-ai-workshop.github.io/">Interpretability in Action : Present, Past and Future</a> . We have 3 tracks : <b>Regular, Published and Position papers</b>!</div><div>Submission <b>deadline is 30 August 2024</b>. Consider submitting and find the CFP below!</div><div><br></div><div>If you are <b>interested in reviewing, please fill this form</b> : <a href="https://docs.google.com/forms/d/e/1FAIpQLSfZ12cMjq8NkFpmGSnZiQcdO35yd3szn_Skq00P5eUFhWUVgA/viewform">https://docs.google.com/forms/d/e/1FAIpQLSfZ12cMjq8NkFpmGSnZiQcdO35yd3szn_Skq00P5eUFhWUVgA/viewform</a></div><div><br></div><div><b>Help us spread the word by sharing in your institutes!</b></div><div>************************</div><div><br></div><div><h1 id="gmail-call-for-papers" style="box-sizing:border-box;padding:0px;margin:1.5rem 0px 1rem;font-size:2.5rem;color:rgb(0,0,0);border-width:0px 0px 1px;border-style:solid;border-color:rgb(230,230,230);font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif">Call for Papers</h1></div><div><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">We invite submissions to the workshop on interpretability in machine learning, titled “Interpretable AI: Past, Present and Future”. This workshop aims to bridge classical interpretability research with modern methods for foundation models, fostering discussions on the mathematical foundations, methodology, design, evaluation, and application of interpretable machine learning models.</p><h2 id="gmail-topics-of-interest" style="box-sizing:border-box;padding:0px;margin:1.5rem 0px 1rem;font-size:1.9rem;color:rgb(0,0,0);border-width:0px 0px 1px;border-style:solid;border-color:rgb(230,230,230);font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif">Topics of Interest<a class="gmail-anchor gmail-d-print-none" aria-hidden="true" style="box-sizing:border-box;color:rgb(204,204,204);margin-left:0.25rem;opacity:0"><span class="gmail-fas gmail-fa-anchor" style="box-sizing:border-box;display:inline-block;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;line-height:1;font-family:"Font Awesome 5 Free";font-size:0.85rem"></span></a></h2><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">We welcome submissions addressing, but not limited to, the following topics:</p><ul style="box-sizing:border-box;padding:0px;margin:1rem 0px 1rem 1.5rem;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px"><li style="box-sizing:border-box">Novel approaches, methodologies, and foundations for interpretability in machine learning</li><li style="box-sizing:border-box">Metrics and benchmarks for evaluating the quality and reliability of interpretable models</li><li style="box-sizing:border-box">Mechanistic interpretability methods for foundation models (e.g.: Large Language Models and Diffusion models)</li><li style="box-sizing:border-box">Comparative studies on different interpretability methods and their applications</li><li style="box-sizing:border-box">Integration of domain knowledge and expertise in interpretable model design</li><li style="box-sizing:border-box">Applications of interpretability in diverse domains such as healthcare, earth sciences, material sciences, physics, and beyond</li><li style="box-sizing:border-box">Exploration of ethical and legal needs for enforcing interpretable models in decision-making processes</li></ul><h2 id="gmail-submission-guidelines" style="box-sizing:border-box;padding:0px;margin:1.5rem 0px 1rem;font-size:1.9rem;color:rgb(0,0,0);border-width:0px 0px 1px;border-style:solid;border-color:rgb(230,230,230);font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif">Submission Guidelines<a class="gmail-anchor gmail-d-print-none" aria-hidden="true" style="box-sizing:border-box;color:rgb(204,204,204);margin-left:0.25rem;opacity:0"><span class="gmail-fas gmail-fa-anchor" style="box-sizing:border-box;display:inline-block;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;line-height:1;font-family:"Font Awesome 5 Free";font-size:0.85rem"></span></a></h2><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">Authors are invited to submit up to <span style="box-sizing:border-box;font-weight:700">6 pages</span> with unlimited references and supplementary materials. Submissions should be <span style="box-sizing:border-box;font-weight:700">anonymized</span> and should use the official <a href="https://www.overleaf.com/read/vjqdmrbfmppm#f22612" style="box-sizing:border-box;font-weight:700;text-decoration-line:none;color:rgb(252,77,80)"><span style="box-sizing:border-box">template</span></a>. Please submit your papers through the official <a href="https://openreview.net/group?id=NeurIPS.cc/2024/Workshop/InterpretableAI" style="box-sizing:border-box;font-weight:700;text-decoration-line:none;color:rgb(252,77,80)"><span style="box-sizing:border-box">openreview portal</span></a>.</p><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">We have three tracks: <span style="box-sizing:border-box;font-weight:700">main track</span>, <span style="box-sizing:border-box;font-weight:700">published paper track</span>, and <span style="box-sizing:border-box;font-weight:700">position paper track</span>.</p><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">Reviewing is double-blind. Submissions should clearly articulate the research problem, methodology, results (if available), and contributions to the field.</p><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">For the <span style="box-sizing:border-box;font-weight:700">main track</span>, submissions can be exploratory in nature and contain initial novel ideas and results. We welcome submissions undergoing concurrent peer review elsewhere. Papers presented or scheduled for presentation at non-archival venues, such as other workshops, are permitted for submission. However, it is the authors’ responsibility to verify compliance with other venues’ policies.</p><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">Submissions that have been previously published or accepted for publication in peer-reviewed conferences or journals should be submitted to the <span style="box-sizing:border-box;font-weight:700">published paper track</span>. These papers will not undergo the review process and will instead be evaluated by ACs based on the paper’s topic and its fit for the workshop.</p><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">We also invite <span style="box-sizing:border-box;font-weight:700">position papers</span> that provide a commentary on the current state of interpretable machine learning or its usage in practice, as these may be of broader interest. To clearly identify submissions, position papers must be titled beginning with the phrase “Position: <Paper title>” and submitted to the <span style="box-sizing:border-box;font-weight:700">position paper track</span>.</p><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">This workshop is <span style="box-sizing:border-box;font-weight:700">non-archival</span>, and will not have formal proceedings. All the accepted papers will be publicly available on our workshop website. The selection of oral presentations will be made based on the PC’s recommendations and their fit to the topics of the workshop.</p><h2 id="gmail-important-dates" style="box-sizing:border-box;padding:0px;margin:1.5rem 0px 1rem;font-size:1.9rem;color:rgb(0,0,0);border-width:0px 0px 1px;border-style:solid;border-color:rgb(230,230,230);font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif">Important Dates<a class="gmail-anchor gmail-d-print-none" aria-hidden="true" style="box-sizing:border-box;color:rgb(204,204,204);margin-left:0.25rem;opacity:0"><span class="gmail-fas gmail-fa-anchor" style="box-sizing:border-box;display:inline-block;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;line-height:1;font-family:"Font Awesome 5 Free";font-size:0.85rem"></span></a></h2><ul style="box-sizing:border-box;padding:0px;margin:1rem 0px 1rem 1.5rem;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px"><li style="box-sizing:border-box">Submission open on OpenReview: August 9, 2024</li><li style="box-sizing:border-box">Submission Deadline: August 30, 2024</li><li style="box-sizing:border-box">Notification of Acceptance: October 9, 2024</li><li style="box-sizing:border-box">Camera-ready Deadline: November 15, 2024</li><li style="box-sizing:border-box">Workshop Date: December 14 or December 15, 2024</li></ul><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">All deadlines are 11:59PM UTC-12:00 (AoE).</p><h2 id="gmail-contact" style="box-sizing:border-box;padding:0px;margin:1.5rem 0px 1rem;font-size:1.9rem;color:rgb(0,0,0);border-width:0px 0px 1px;border-style:solid;border-color:rgb(230,230,230);font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif">Contact<a class="gmail-anchor gmail-d-print-none" aria-hidden="true" style="box-sizing:border-box;color:rgb(204,204,204);margin-left:0.25rem;opacity:0"><span class="gmail-fas gmail-fa-anchor" style="box-sizing:border-box;display:inline-block;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;line-height:1;font-family:"Font Awesome 5 Free";font-size:0.85rem"></span></a></h2><p style="box-sizing:border-box;padding:0px;margin:1rem 0px;font-family:-apple-system,"system-ui","Segoe UI",Helvetica,Arial,sans-serif;font-size:16px">For inquiries, please contact interpretable.ai.neurips.workshop [AT] <a href="http://gmail.com">gmail.com</a>.</p></div></div>