Aug 2026
CoLLAs 2026 (Conference on Lifelong Learning Agents) will take place on 14–17 September 2026 at POLITEHNICA Bucharest. Conference website Sponsors …
Aug 2026
Romanian AI Days 2026 will take place on 18-19 September 2026 at POLITEHNICA Bucharest. Event website BRAIT thesis awards
Teaser for Foundation Models are Implicit Deepfake Detectors
Stefan Smeu, Dragos-Alexandru Boldisor, Elisabeta Oneata, Dan Oneata
Under review Aug 2026
Links: arXiv GitHub Abstract Pretrained self-supervised representations have emerged as a core component of current deepfake detection methods, yet it …
Teaser for Pathways of Visual Information Flow in Vision-Language Models
Israfel Salazar, Stella Frank, Dan Oneata, Desmond Elliott, Constanza Fierro
Under review Jul 2026
Links: arXiv Abstract We study how visual information is routed in vision-language models (VLMs). Using causal patching on controlled synthetic and …
Teaser for Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning
Cristian-Teodor Neamtu, Serban Mihalache, Stefan Smeu, Dan Oneata, Horia Cucu, Dragos Burileanu
Accepted at EUSIPCO 2026 Jun 2026
Links: arXiv Abstract The proliferation of text-to-speech (TTS) systems capable of generating realistic synthetic speech poses growing challenges for …
Teaser for idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
Andrada Gobeaja, Ionut Hodoroaga, Elena Burceanu, Marius Leordeanu
Under review May 2026
Links: arXiv Abstract Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave …
Teaser for How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
Teodor-Mihai Stupariu, Andrei Manolache
Accepted at ICML 2026 Workshop on Weight-Space Symmetries May 2026
Links: arXiv Abstract Equivariant neural networks encode geometric symmetries by construction, yet they are often difficult to optimize and can …
Teaser for Protein Fold Classification at Scale: Benchmarking and Pretraining
Dexiong Chen, Andrei Manolache, Mathias Niepert, Karsten Borgwardt
Accepted at ICML 2026 (Oral) May 2026
Links: arXiv GitHub Abstract Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of …
May 2026
Final project posters from the DeepFMI 2026 edition are now online! View the gallery.
Teaser for Revisiting Adam for Streaming Reinforcement Learning
Florin Gogianu, Adrian Catalin Lutu, Razvan Pascanu
Accepted at Reinforcement Learning Conference (RLC) 2026 May 2026
Links: arXiv Abstract Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, …