3rd International Conference on Neuro-Symbolic Systems (NeuS)
University of Southern California
June 16-18, 2026
3rd International Conference on Neuro-Symbolic Systems (NeuS)
University of Southern California
June 16-18, 2026
NeuS aims to bring together novel concepts, theories, and practices that can help in the development of the science and application of neuro-symbolic computing and systems. The conference will focus on system theoretic approaches to address fundamental challenges to increase the confidence of neuro-symbolic systems by making them more secure, dependable, and trustworthy. An emphasis will be on design, analysis, and synthesis techniques for neuro-symbolic systems with a particular interest in assurance metrics, robustness, and ease of translation from design to production.
This year, NeuS will be co-located with the 8th Annual Learning for Dynamics & Control Conference (L4DC). Both conferences will be held on the campus of the University of Southern California (USC), which is around 3 miles south of downtown Los Angeles. USC is the largest private university in Southern California, and is well-connected to the rest of the city by LA Metro. It is also close to a number of museums.
A "call for papers flyer" (PDF) is available here.
The conference aims to advance the development of principled approaches to the design, development, and deployment of complex and sophisticated neuro-symbolic systems. Topics of particular interest are:
Artificial Intelligence
Machine Learning
Autonomy
Cyber-Physical Systems
Formal Methods
Foundational Models
Neurosymbolic Programming
Neurosymbolic Hardware
New research papers: papers that report new research in areas of interest to NeuS. We particularly encourage submissions that cross traditional area boundaries and address the core neuro-symbolic themes listed above.
Tutorial-style papers: papers that explain concept(s) from a subset of the sub-communities of NeuS in a form accessible to all of the areas served by NeuS.
Challenge problem and case study papers: papers that describe challenge problems of interest to NeuS or describe industrial-scale case studies employing existing research results, software, or hardware.
As part of submissions, we also strongly encourage submission of tools or datasets that can advance the field. The program will comprise a few keynotes, tutorials, contributed oral presentations, and poster presentations.
All papers will be published on the Proceedings of Machine Learning Research (PMLR) series. All submissions can be up to 10 pages in length (except for tutorial papers that can have 20 to 30 pages), in the PMLR format, excluding references and appendices. All papers will be peer reviewed. Note that reviewers are not expected to read material in the appendix, and the paper's results must be understandable from the material in the main paper. Papers should be submitted through Open Review. The review process is only single-blind, i.e., author names should be listed on the papers, but reviewers are anonymous to authors.
Policy on the use of Gen AI: NeuS will use the IEEE CSS Generative AI guidelines available here.