Lisbon, Portugal, July 24–25
co-located with FLoC 2026
https://aiverification.org/2026/
=== Important Dates (all dates are 11:59 AM AoE) ===
Abstract Submission: March 19, 2026
Paper Submission: March 26, 2026
Paper Notification: May 15, 2026
Poster Submission: June 11, 2026
Poster Notification: June 18, 2026
=== SAIV ===
The International Symposium on AI Verification (SAIV) aims to bring together researchers from the communities on formal methods and artificial intelligence. Formal reasoning about learning-based systems raises novel, challenging, and exciting problems, such as the verification of learning-based components, the combination of deep learning and symbolic algorithms, and the data-driven verification of systems. SAIV aims to serve as a platform for idea exchange and cross-pollination on these topics.
=== 2026 Edition ===
SAIV 2026 will feature a keynote by Armando Solar-Lezama (MIT) and four invited speakers: Lars Lindemann (ETH Zurich), Sara Magliacane (University of Amsterdam), Lenka Tětková (Technical University of Denmark), and Đorđe Žikelić (Singapore Management University).
SAIV 2026 will host the 7th International Verification of Neural Networks Competition (VNN-COMP'26) (https://vnn-comp.github.io/).
=== Submission ===
We invite three categories of submissions:
**Original papers** describe original research and sufficient detail to assess the merits and relevance of the submission. For papers reporting experimental results, authors are strongly encouraged to make their data available. We welcome both short and long papers. Submissions should not exceed 18 pages (LNCS format).
**Benchmark and case-study papers** propose a challenge to the SAIV community or showcase practical evaluations, real-world applications, or lessons learned in verifying and deploying safety-critical AI systems, focusing on metrics, methodologies, and safety outcomes.
**Presentation-only papers**: SAIV aims to integrate researchers from the AI and FM communities. Papers from these areas are dispersed across many conferences. A visit to SAIV should offer a wide picture of the latest research in the field. Thus, we welcome presentations of papers that will not appear in the proceedings.
In addition, VNN-COMP will invite competition contribution papers from participants for both tools and benchmarks that will also appear in the proceedings through a separate call; see the VNN-COMP website for more details.
Papers selected for publication will appear in Springer's LNCS proceedings.
=== Topics ===
The topics covered by SAIV include, but are not limited to, the following:
Safety specifications for systems with AI components
Symbolic analysis of cyber-physical systems with AI components
Formal verification of neural networks
Neuro-symbolic reasoning for AI safety
Testing approaches for systems with AI components
Formal guarantees for interpretable AI
Machine learning for program and controller synthesis
Machine learning for automated reasoning and theorem proving
Differentiable proof certificates
Statistical approaches to falsification and verification
Data-driven verification
=== Program Chairs ===
Guy Avni (University of Haifa)
Christian Schilling (Aalborg University)
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************
Posts
