<div dir="ltr"><span dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:20pt;margin-bottom:6pt"><span style="font-size:20pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Call for Papers for UCRL workshop at ICLR 2026</span></span><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">ICLR 2026 workshop on Unifying Concept Representation Learning</span></p><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><a href="https://ucrl-iclr26.github.io/" target="_blank" rel="nofollow" style="text-decoration-line:none;color:rgb(26,115,232)"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(17,85,204);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;text-decoration-line:underline;vertical-align:baseline">https://ucrl-iclr26.github.io/</span></a></p><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><span dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:18pt;margin-bottom:6pt"><span style="font-size:16pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Motivation</span></span><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Several areas at the forefront of AI research are currently witnessing a convergence of interests around the problem of </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">learning high-quality concepts from data</span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">. Concepts have become a central topic of study in </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">neuro-symbolic integration (NeSy).</span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> NeSy approaches integrate perception – usually implemented by a neural backbone – and symbolic reasoning by employing concepts to glue together these two steps: the latter relies on the concepts detected by the former to produce suitable outputs. Concepts are also used in </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Explainable AI (XAI)</span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> by recent post-hoc explainers and self-explainable architectures as a building block for constructing high-level justifications of model behavior. Compared to, e.g., saliency maps, these can portray a more abstract and understandable picture of the machine’s reasoning process, potentially improving interpretability, interactivity, and trustworthiness, to the point that concepts have been called the lingua franca of human-AI interaction. </span></p><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">NeSy and XAI methods hinge on learned concepts being “high-quality”. Concepts with </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">misaligned semantics </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">may compromise the meaning of model explanations, out-of-distribution behavior of NeSy architectures and human understanding of the underlying systems. Recent works propose to leverage disentangled representations to mitigate concept leakage, i.e., the presence of irrelevant information in the learned concepts. </span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Causal Representation Learning (CRL)</span><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"> is a generalization of disentangled representation learning, when the latent variables are dependent on each other, e.g., due to causal relations. </span></p><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">The potential of leveraging CRL to learn more robust and leak-proof concepts is an emerging area of research with a growing number of approaches, but many open questions remain. In particular, what properties high-quality concepts should satisfy is unclear. Moreover, despite studying the same underlying object,  research in NeSy, XAI and CRL is proceeding on mostly independent tracks, with minimal knowledge transfer. Separate branches differ in their working definitions of what concepts are and what desiderata they ought to satisfy, on what data and algorithms they should be learned with, and on how to properly assess their quality. This also means that approaches in one area often ignore insights from the others. As a result, the central issue of how to properly learn and evaluate concepts is largely unanswered. </span></p><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">The aim of this ICLR 2026 workshop is to bring together researchers from NeSy, XAI and CRL and from both industry and academia, who are interested in learning robust, semantically meaningful concepts. We welcome submissions on the following topics:</span></p><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><ul style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;margin-top:0px;margin-bottom:0px"><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Foundations of concept representations and learning in XAI, CRL and NeSy.</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Supervised and unsupervised techniques for learning concepts from observational and interventional data, raw inputs, and pre-trained embeddings.</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Techniques for learning concepts in non-standard settings, e.g., causal abstraction.</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Design and evaluation of concept-based XAI techniques and self-explainable concept-based models.</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Interactive human-machine concept acquisition and alignment.</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Applications of concept-based AI systems, including but not limited to, reasoning, causality, formal verification, interactive learning, and explainability.</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Metrics and evaluation techniques for assessing the quality of learned concepts, with a focus on down-stream applications.</span></p></li></ul><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><span dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:18pt;margin-bottom:6pt"><span style="font-size:16pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Important Dates & Details </span></span><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Paper submission deadline: January 30th, 2026 23:59 AoE</span></p><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Notification to authors: March 1st, 2026 23:59 AoE</span></p><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Workshop date: April 26 or 27, 2026</span></p><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Workshop location: Rio de Janeiro, Brazil</span></p><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline"><br></span></p><span dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:18pt;margin-bottom:6pt"><span style="font-size:16pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Submission instructions </span></span><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">We invite submissions on on-going research that have not yet been published in a venue with proceedings. While we welcome unfinished work, submissions in this track should contain original ideas, new connections between research fields, or novel results. Submissions should be formatted using the ICML latex template and formatting instructions. Papers should be up to 6 pages in length, including all main results, figures, and tables. Appendices containing additional details are allowed, but reviewers are not expected to take this into account.</span></p><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><p dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Submission Link: </span><a href="https://openreview.net/group?id=ICLR.cc/2026/Workshop/UCRL#tab-your-consoles" target="_blank" rel="nofollow" style="text-decoration-line:none;color:rgb(26,115,232)"><span style="font-size:11pt;font-family:Arial,sans-serif;color:rgb(17,85,204);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;text-decoration-line:underline;vertical-align:baseline">https://openreview.net/group?id=ICLR.cc/2026/Workshop/UCRL#tab-your-consoles</span></a></p><br style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px"><span dir="ltr" style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;line-height:1.38;margin-top:18pt;margin-bottom:6pt"><span style="font-size:16pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Organization committee</span></span><ul style="color:rgba(0,0,0,0.87);font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif;font-size:14px;margin-top:0px;margin-bottom:0px"><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Amit Dhurandhar (IBM Research)</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Amir-Hossein Karimi (U Waterloo)</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Sara Magliacane (U Amsterdam)</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Stefano Teso (U Trento)</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Efthymia Tsamoura (Huawei Research)</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" role="presentation" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;font-variant-alternates:normal;vertical-align:baseline">Zhe Zeng (U Virginia)</span></p></li></ul></div>