3 citations · 4 across the 3 of their papers we have counts for
4 papers
Monitoring latent reasoning in looped language models
Pawel Olszowiec, Paulina Tomaszewska, Maciej Żelaszczyk +2
Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage cost. Despite their rising pop…
Interpretable Multi-task Learning with Shared Variable Embeddings
Maciej Żelaszczyk, Jacek Mańdziuk
This paper proposes a general interpretable predictive system with shared information. The system is able to perform predictions in a multi-task setting where distinct tasks are no…
Text-to-Image Cross-Modal Generation: A Systematic Review
Maciej Żelaszczyk, Jacek Mańdziuk
We review research on generating visual data from text from the angle of "cross-modal generation." This point of view allows us to draw parallels between various methods geared tow…
Adversarial defenses via a mixture of generators
Maciej Żelaszczyk, Jacek Mańdziuk
In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in…