Presentation from the cdis conference: play.kth.se/media/Automate…

Lovely slide 🙃

🏃‍♂️

My thesis is now available: kth.diva-portal.org/smash/record.j…

📝

Look forward to start my international postdoc at Arizona before moving on to Unimelb and Imperial!

> google scholar recommends RL paper on real-life task X (environmental engr today) > click immediately > get to experiment section > simulation results only > close browser

A recording of my guest lecture at ASU on aggregation for approximating POMDPs is available here: youtube.com/watch?v=gsD2Jg… Thanks to Dimitri Bertsekas and Yuchao Li for organizing this!

Very insightful talk on the theory of RL!

I am pleased to share the full set of videolectures, slides, textbook, and other supporting material of the 7th offering of my Reinforcement Learning class at ASU, which was completed two days ago; check web.mit.edu/dimitrib/www/R…

Sharing my new paper (joint with Yuchao Li and Kim Hammar) on Feature-Based Belief Aggregation for Partially Observable Markov Decision Problems," lnkd.in/ebZUiJxT The paper gives favorable computational results involving very large scale problems #ReinforcementLearning

I am pleased to share my new paper (w/ Kim Hammar, Yuchao Li, Tansu Alpcan, and Emil Lupu) on "Adaptive Network Security Policies via Belief Aggregation and Rollout," web.mit.edu/dimitrib/www/H… It deals with rollout algorithms and applications in cybersecurity.

Using lightweight LLMs to cut incident response times and reduce hallucinations - helpnetsecurity.com/2025/08/21/lig… - University of Melbourne Imperial College London Kim Hammar Emil Lupu #IncidentResponse #AI #LLM #research #CISO #ITsecurity #CyberSecurityNews #SecurityNews

I am pleased to see our recent research featured in the news. We hope both academia and industry will find this useful as a foundation for further research and practical deployment. A preprint of the article is available here: lnkd.in/dARFtQnY

Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination (DEMO): youtube.com/watch?v=XXo4Y6…

As a researcher at a frontier lab I’m often surprised by how unaware of current AI progress public discussions are. I wrote a post to summarize studies of recent progress, and what we should expect in the next 1-2 years: julian.ac/blog/2025/09/2…

the hardest part of machine learning isn’t the math. it’s reproducing someone else’s paper without losing your mind.

Pleasure to give a talk at CityU in Hong Kong, kindly invited by Prof. Tao Li

CSLE 0.9.0 was just released, have a look: github.com/Limmen/csle

Pleasure to visit city university of Hong Kong. Thanks to Tao Li for the invitation!