Romanian AI Days, dedicated to the Artificial Intelligence community in Romania, aims to provide a venue for learning and networking for all those interested in AI and related fields (from beginners to experts, academic and industry practitioners, freelancers, students of any level, etc), and to better connect the AI community in Romania to the international community.

The event consists of two days of keynotes on recent advancements in the field, round tables on community, public policies, startups, poster session with presentations from junior practitioners, and ample opportunities for networking.

Press release

List of posters presented at the 2023 edition (alphabetical order by the first name of the first author):

1. Alex-Mihai Serafim, Radu Filipescu - Zero-shot anomaly detection without foundation models

2. Alexandru Olaru, Sorin Grigorescu -- KP2D: Neural outlier rejection for self-supervised keypoint learning

3. Alina Marcu, Mihai Pirvu, Dragos Costea, Emanuela Haller, Emil Slusanschi, Ahmed Nabil Belbachir, Rahul Sukthankar, Marius Leordeanu -- Self-supervised hypergraphs for learning multiple world interpretations

4. Bogdan Muntean, Mihai Zaha, Sorin Grigorescu -- A deep learning perception and control system for legged robots

5. Bogdan Musat, Razvan Andonie -- Pruning convolutional filters via Reinforcement Learning with entropy minimization

6. Dragos Costea, Alina Marcu, Alexandra Budisteanu, Marius Leordeanu -- GeoView: Self-supervised novel 2D view synthesis of large-scale scenes with multi-scale geometric constraints

7. Dragos-Constantin Tantaru, Elisabeta Oneata, Dan Oneata -- Weakly-supervised deepfake localization in diffusion-based images

8. Florin Brad, Ioana Pintilie, Andrei Manolache -- Time series anomaly detection using diffusion-based models

9. Florin Condrea, Saikiran Rapaka, Lucian Itu, Puneet Sharma, Jonathan Sperl, A Mohamed Ali, Marius Leordeanu -- Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms

10. Imre Gergely Mali, Leveraging multi-agent Deep Reinforcement Learning in cluster resource management

11. Ionel Hosu, Traian Rebedea, Stefan Trausan-Matu -- Disentangling exploration and exploitation in Deep Reinforcement Learning using contingency awareness

12. Iuliana-Renata Sirbu, Iustin Sirbu, Jasmina Bogojeska, Traian Rebedea -- Clinical report generation powered by Machine Learning

13. Iulian-Marius Taiatu, Andrei-Marius Avram, Dumitru-Clementin Cercel, Florin Pop -- RoBERTweet: A BERT language model for Romanian tweets

14. Marian Abagiu - Industrial applications with Computer Vision and Machine Learning in Automotive

15. Marius Dragoi, Ioana Pintilie, Dragos Tantaru, Andrei Manolache, Florin Brad -- AsmLLM: Large language models for assembly code

16. Marius Dragomir, Lucian Busoniu, Florin Gogianu -- Resilience to pruning in Deep RL

17. Mihai Cristian Pirvu, Alina Marcu, Alexandra Odobescu, Nabil Belbachir, Marius Leordeanu -- Multi-layer hypergraphs for semi-supervised learning using Earth observations

18. Mihai Ivanovici, C. Florea, A. Cataron, R. Coliban, I. Plajer, A. Baicoianu, S. Oprisescu, L. Majercsik, S. Popa, K. Marandskiy, G. Feldioreanu, Gh. Olteanu, A. Manea, L. Dogar -- AI-based applications on Earth observation data for Agriculture

19. Mihai-Octavian Luca -- Coast Guard: An automated phishing detection platform

20. Mihai Masala, Nicolae Cudlenco, Traian Rebedea, Marius Leordeanu -- Explaining Vision and Language through graphs of events in space and time

21. Nwaeke Daniel Chijindu, Sorin Grigorescu -- Detection of damaged metal plates using a convolutional neural network

22. Radu-Constantin Flesar, Sebastian-Aurelian Stefniga, Paul Farago, Robert Radu Ilean -- Patient gait monitoring classification for Parkinsons disease

23. Rares Horju, Sorin Grigorescu -- RGBD HyperNet: A meta-learning approach to the task of semantic segmentation

24. Sebastian Mocanu, Marius Leordeanu -- Efficient scene understanding and real-time semantic control for autonomous UAVs

25. Sebastian-Antonio Toma -- Asking the right questions: Enhance the learning capabilities of a generative model

26. Stefan Smeu, Elena Burceanu, Emanuela Haller, Andrei Liviu Nicolicioiu -- Environment-biased feature ranking for novelty detection robustness

27. Teodor Poncu, Vlad Florea -- Adapting & aligning large language models to targeted code-gen tasks

DIAMOND

GOLD

SILVER

If you are interested in supporting the event, please get in touch at contact at airomania dot eu to learn about the benefits for sponsors.