Dissemination

Conference presentations

• 20th DECSoS Workshop on Dependable Smart Cyber- physical Systems and Systems-of-Systems, September 9th, Stockholm, Sweden

Workshop at SAFECOMP ,AIT

• RV 2025, 25th International Conference on Runtime Verification, September 15-19, 2025, Graz, Austria

Hidden-Layer Monitoring for Out-of-Distribution Localization in Image Segmentation, MU

Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs, CHALM, CSX-AI, UOL

• Summer School on Artificial Intelligence and Cybersecurity, 22-26 September 2025, Vienna, Austria

Robustness Certification of AI and Generative AI, ULIV

• ACM/IEEE International Conference on Human-Robot Interaction (HRI), 16-19 March 2026, Edinburgh, Scotland, UK

Towards a Framework for Studying Alignment Drift in Multi-Turn Human–Robot Interaction, CHALM

• Robotics Seminar at the University of Bristol, 25 March 2026

Learning Temporal Specifications from Examples of System Behavior, ULIV

• SynCoP 2026, 11th International Workshop on Synthesis of Convex| Parameters, Torino, Sunday 12th April 2026

Synthesizing Temporal Specifications via  Learning from Examples of System Behavior ,ULIV

• ACL, The 64th Annual Meeting of the Association for Computational Linguistics, 2nd -7th July 2026, San Diego, California

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage ,ULIV

• CAV 2026, 38th International Conference on Computer Aided Verification, July 26-29 2026 in Lisbon, Portugal

Sweap: Reactive Synthesis for Infinite-State Integer Problems,TUW

• TAROT Summer School 2026, Testing, Validation, and Security of AI-enabled Systems, 13–17 July 2026, Munich, Germany

Formal verification of deep neural networks, AIT

Engineering Workflow, Reimagined with Agentic AI, SISW

Agentic AI: Foundations and Failure Modes, TUW

• IROS 2026, The IEEE/RSJ International Conference on Intelligent Robots and Systems, September 27 – October 1, 2026, Pittsburgh, USA

Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation

 

Conferences posters

• NeurIPS 2025, Dec 2nd – 7th, 2025, San Diego, CA

Explainably Safe Reinforcement Learning

• EMNLP 2025, November 4 – 9, Suzhou, China

Randomized Smoothing meets Vision-Language-Models

• ICLR 2026, April 23rd – 27th, 2026, Rio de Janeiro, Brazil

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models

• ACL 2026, July 2nd – 7th 2026, San Diego, California

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage

• ICML 2026, July 6th – 11th, Seoul, South Korea

Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs

• IROS 2026, Sept 27 – oct 1, Pittsburgh, PA, USA

Safety-Constrained Reinforcement Learning with PostTraining Reachability Verification for Robot Navigation

 

 

 

 

 

 

 

• Natan Levy et al., Statistical Runtime Verification for LLMs via Robustness Estimation | RV 2025 from September 15–19, 2025 Graz, Austria
• Chih-Hong Cheng et al., Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs | RV 2025 from September 15–19, 2025 Graz, Austria
• Yuan Gao et al., Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
• Jinwei Hu et al.,DDSA: Dual-Domain Strategic Attack for Spatial-Temporal efficiency in adversarial robustness testing | ICASSP 2026 from 4-8 May 2026, Barcelona, Spain
• Tora Bodin & Ilaria Torre, Towards a Framework for Studying Alignment Drift in Multi-Turn Human–Robot Interaction | HRI’26 Edinburgh Scotland from March 16-18, 2026
• Ayelet Berzack & Guy Katz, On Integrating Large Language Models and Scenario-Based Programming for Improving Software Reliability | MODELSWARD March 2026, Marbella Spain
• Xinmiao Huang et al., Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models, April 23rd – 27th, 2026, Rio de Janeiro, Brazil
• Boxuan Wang et al.,Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models | ACL 2026 San Diego, California, from July 2 – 7, 2026
• Jinwei Hu et al., Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage | ACL 2026 San Diego, California, from July 2 – 7, 2026
• Ido Pinto et al., Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs | ICML, Seoul, South Korea July 6th – 11th, 2026
• Luca Di Stefano et al., Sweap: Reactive Synthesis for Infinite-State Integer Problems | CAV 2026, July 26-29 2026 in Lisbon, Portugal, as part of FLoC 2026
• Julian Muller et al., Robust Translation of Natural Language into Traffic Sequence Charts and Co-Simulation with Human Driver Models | IJCAI-ECAI, Bremen, Germany, 15-21 of August 2026
• Luca Marzari and Enrico Marchesini, Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning | IJCAI-ECAI, Bremen, Germany, 15-21 of August 2026
• Luca Marzari, Ezio Bartocci and Enrico Marchesin, A Survey on the Verification of Reinforcement Learning Policies | IJCAI-ECAI, Bremen, Germany, 15-21 of August 2026
• Xiangyu Yin et al., ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning | ECML PKDD 2026, Naples, Italy, from 7 to 11 September 2026
• Dejan Nickovic, STL-Witness: Signal Generation from STL Specifications | RV 2026, Canada, 6-9 october 2026
• Saddek Bensalem, Autonomy as Controlled Transformation: A Formal Theory of Governable AI Systems | ISoLA 2026, Kos, Greece, October 24–28, 2026
• Xiangyu Yin et al., Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration | EMNLP 2026, Budapest, 24 -28 October 2026
• Qisong He et al, Safety-Constrained Reinforcement Learning with PostTraining Reachability Verification for Robot Navigation | IROS 2026, 27 Sept – 01 Oct 2026