This work introduces a recursive parameter sharing construction (RePA) that fosters efficiency without assuming independence, and shows empirically that RePA can greatly reduce time and memory consumption while yielding competitive likelihoods.
Charles Bricout, Gennaro Gala, Viacheslav Borovitskiy et al.· 0 citations
Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. However, their explanations are often derived heuristically. Building on formal explainability, we argue they should also be faithful, i.e.,...
S. Teso, E. Marconato, Steve Azzolin et al.· 0 citations
Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic knowledge and reasoning about how to apply it. However, existing LLM pipelines are opaque, with no explicit separation between these two components. We argue that for well-k...
Nickil Maveli, Antonio Vergari, Shay B. Cohen· 0 citations
Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making them particularly suitable for high-stakes applications where compliance with domain knowledge is essential. A key bottleneck in this paradigm is the a...
Samuele Bortolotti, Wei-Xin Chen, Han Zhao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.