Multi-Agent Reinforcement Learning Boosts Video Game Level Design

Researchers reframe video game level creation as a multi‑agent reinforcement learning task, cutting cost and improving adaptation to new map shapes. Presented at AAAI 2025. Read more: getnews.me/multi-agent-reinforcemen... #multiaigame #aaai2025

New publication on the parameterized complexity of caching in networks accepted at AAAI 2025 - ELASTIC Project The full publication is availabe on project Zenodo repository.

New #ELASTIC work at #AAAI2025: TU Wien & Telefónica Research map the complexity of caching in networks — key for #EdgeComputing & #6G.

🔗 elasticproject.eu/new-publicat...

#ELASTICproject #AI #DistributedSystems

Interview with Filippos Gouidis: Object state classification - ΑΙhub

In our latest interview with AAAI / @acmsigai.bsky.social doctoral consortium participants, we met with Filippos Gouidis to find out more about his work on object state classification #AAAI2025
aihub.org/2025/05/20/i...

#AAAI2025 workshops round-up 3: Neural reasoning and mathematical discovery, and AI to accelerate science and engineering - ΑΙhub

Our third article containing summaries from workshop organisers at #AAAI2025. Find out their key takeaways from their events.

Interview with Onur Boyar: Drug and material design using generative models and Bayesian optimization - ΑΙhub

Great to chat to Onur Boyar about his research designing molecules and crystals using generative models, latent space representations, and optimization techniques. Onur took part in the AAAI / @acmsigai.bsky.social doctoral consortium at #AAAI2025

#AAAI2025 outstanding paper – DivShift: Exploring domain-specific distribution shift in large-scale, volunteer-collected biodiversity datasets - ΑΙhub

Find out more about research that won the AAAI-25 outstanding paper award – AI for social alignment track. In this blog post, Elena Sierra and Lauren Gillespie share the key contributions of their paper #AAAI2025

Interview with Eden Hartman: Investigating social choice problems - ΑΙhub

Hear from Eden Hartman about work “Reducing Leximin Fairness to Utilitarian Optimization”, presented at #AAAI2025.

aihub.org/2025/04/24/i...

Provably safe certification for machine learning models under adversarial attacks: Interview with Chen Feng - ΑΙhub

In our latest interview, we hear from Chen Feng about work presented at #AAAI2025 on safe certification for ML models under adversarial attacks
aihub.org/2025/04/15/p...

AI with, for and by everyone can help maximize its benefits Involving a wider swatch of people in AI development can help maximize its benefits.

Just as the human species got better by learning across cultures and generations, #AI can advance by involving a wider range of people in its development.

Excited to see this news piece on our #AAAI2025 work, with co-authors from around the world 🌎🌍🌏

🔗 cse.engin.umich.edu/stories/ai-w...

Interview with Lea Demelius: Researching differential privacy - ΑΙhub

In the next of our interviews with AAAI / @acmsigai.bsky.social Doctoral Consortium participants, we hear from Lea Demelius about her work on differential privacy #AAAI2025

Interview with AAAI Fellow Roberto Navigli: multilingual natural language processing - ΑΙhub

In our latest interview with the 2025 AAAI Fellows, we chatted to Roberto Navigli about some of the big research projects he's led, some tips for early-career researchers, and why it's important to follow your passion. #AAAI2025

#AAAI2025 workshops round-up 1: Artificial intelligence for music, and towards a knowledge-grounded scientific research lifecycle - ΑΙhub

The organisers from two of the #AAAI2025 workshops tell us their key takeaways from their events

Interview with Tunazzina Islam: Understand microtargeting and activity patterns on social media - ΑΙhub

In the latest interview in our series featuring the AAAI /
@acmsigai.bsky.social doctoral consortium participants, Tunazzina Islam tells us about her work on computational social science, NLP, and social media mining and analysis. #AAAI2025

📃 The publication "Linking Industry Sectors and Financial Statements: A Hybrid Approach for Company Classification" by Guy-Stephane Waffo Dzuyo (Loria - Forvis Mazars), G. Guibon @LipnLab, C. Cerisara (Loria) and L. Belmar Letelier (Forvis Mazars) was presented last week at #AAAI2025 conference.

Wrapping up an amazing #AAAI2025 in Philadelphia 🇺🇸

We presented our work "Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models"

📝 arxiv.org/abs/2401.07115

Grateful to everyone who engaged with our work for the valuable feedback!

I am excited to share that our BindGPT paper won the best poster award at #AAAI2025! Congratulations to the team! Work led by @artemzholus.bsky.social!

Congratulations to our DTAI researchers for presenting their work at #AAAI2025 #AAAI25 Lennert De Smet, Dimos Tsouros, Liesbeth Allein, Jaron Maene, David Depot,
Ignace Bleukx.

Research poster, student, presentation

If you are at #aaai2025, come by our poster on “Learning Exposure Mapping Functions for Peer Effect Estimation” at the AAAI Workshop on AI with Causal Techniques, presented by my PhD student Shishir Adhikari, to learn how we automatically account for different counterfactual ego network structures.

Thanks to everyone who came to my #AAAI2025 award talk on Saturday. I was gratified to see so many of the people I know and respect in the audience.. 🙏🤗

Here is a recording if you are interested.. 👉
www.youtube.com/watch?v=CQ5J...

Can we effectively detect covert Information Operations (IOs) that attempt to manipulate socio-political debates on social media?

This is the focus of our work, "IOHunter: Graph Foundation Model to Uncover Online Information Operations", just presented at the #AAAI #AAAI2025

@rebeccasaxe.bsky.social giving an informative and thought-provoking talk on theory of mind at the #aaai2025 workshop on Advancing Artificial Intelligence through Theory of Mind (ToM4AI).

It was a pleasure presenting our work "Universality of Real Minimal Complexity Reservoirs" at #AAAI2025. Many thanks for your interest. I look forward to further discussions =). #AAAI #AAAI25

Full paper: arxiv.org/pdf/2408.08071

A slide on data gravity from Andrew Ng’s AAAI 2025 invited talk.

Andrew Ng mentions a processing cost of up to $40 for a gpt4-o-mini request in his #AAAI2025 invited talk about AI, Agents and Applications. I did not fully get what this price includes. Is there any publicly available information about costs of a gpt4-o-mini prompt?

Second #AAAI2025 demo complete! Image featuring the verbal and non-verbal engagement of Dr. Ken Forbus

If you're at #AAAI2025, come check out our demo on neurosymbolic reinforcement learning with probabilistic logic shields 🤖 Tomorrow (Sat, March 1) from 12:30–2:30 PM during the poster session 💻

Learning in games usually assumes small action spaces. This afternoon at #AAAI2025 we give an oral presentation showing that the PDCoEA co-evolutionary algorithm finds the Nash Equilibrium of the game below (2^n actions) in expected poly(n) time. Joint work with Shishen Lin.

There’s a lot of PhD advisors who are neglecting key parts of their jobs. Your students should NEVER have 100s of words of text on a slide, nor a grainy image of a LaTeX table (bar charts please!) A good talk is now the exception not the norm. It’s all conferences - not just #AAAI2025

Decided last minute to come to #AAAI2025 for the day. Hit me up if you are in Philly.

GenPlan: Generative Sequence Models as Adaptive Planners Sequence models have demonstrated remarkable success in behavioral planning by leveraging previously collected demonstrations. However, solving multi-task missions remains a significant challenge, par...

🚀 Exciting news! Our paper "GenPlan: Generative Sequence Models as Adaptive Planners" is accepted at #AAAI2025! 🎉

Heartfelt thanks to Prof. @yvpant.bsky.social for his invaluable guidance!

🔗 Paper: arxiv.org/abs/2412.08565
🌐 Project: aku02.github.io

(1/🧵) ⬇️

Here's my student Sheikh Mannan drawing an audience demonstrating real-time AI task guidance in disoriented balancing. If you're at #AAAI2025 stop by tomorrow for another (different) demo!