Still searching for a research topic? #FMAS2024 discussion session might provide some inspiration!
https://buff.ly/sH6P7TM
Still searching for a research topic? #FMAS2024 discussion session might provide some inspiration!
app.mural.co/t/phd3063/m/...

The lovely people @dblp have indexed the proceedings from #FMAS2024 (thanks!)

If you want to take a look at the sort of work that #FMAS2025 is interested in, what better place to look than last year's proceedings.

Here they are, via DBLP: https://dblp.dagstuhl.de/db/series/eptcs/eptcs411.html

dblp: FMAS@iFM 2024

Bibliographic content of FMAS@iFM 2024

FMAS Challenges 2024

mural.co
FMAS Challenges 2024

mural.co

The invited talks from #FMAS2024 are captured on our YouTube channel: https://buff.ly/3QFxNhE

You can (re)watch "Proof for Industrial Systems using Neural Certificates" by Daniel Kröning (joint with #iFM2024) and "Self-Adaptation in Autonomous Systems" by Lizeth Tarifa

#FormalMethods
@FMASWorkshop

Before you continue to YouTube

New paper

"Formalizing Stateful Behavior Trees"
by Serena S. Serbinowska, Preston Robinette, Gabor Karsai, and Taylor T. Johnson

https://buff.ly/4fNOTFg

#FMAS2024

EPTCS: Formalizing Stateful Behavior Trees

New paper

"Open Challenges in the Formal Verification of Autonomous Driving"
by Paolo Burgio, Angelo Ferrando, and Marco Villani

https://buff.ly/4eIsJCQ

#FMAS2024

EPTCS: Open Challenges in the Formal Verification of Autonomous Driving

New Paper

"Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report"
by Syed Ali Asadullah Bukhari, Thomas Flinkow, Medet Inkarbekov, Barak A. Pearlmutter, and Rosemary Monahan

https://cgi.cse.unsw.edu.au/~eptcs/paper.cgi?FMAS2024.12

#FMAS2024

EPTCS: Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report

New paper

"Model Checking for Reinforcement Learning in Autonomous Driving: One Can Do More Than You Think!"
by Rong Gu

https://cgi.cse.unsw.edu.au/~eptcs/paper.cgi?FMAS2024.11

#FMAS2024

EPTCS: Model Checking for Reinforcement Learning in Autonomous Driving: One Can Do More Than You Think!