3 papers
stat.ML2026
High-probability guarantees for linear accessibility in feature superposition
Enrico Vompa
Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear accessibility of simultaneously act…
cs.AI2026
The Scaling Properties of Implicit Deductive Reasoning in Transformers
Enrico Vompa, Tanel Tammet
We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelating provability from spurious fea…
cs.CV2025
Beyond the Linear Separability Ceiling: Aligning Representations in VLMs
Enrico Vompa, Tanel Tammet, Mohit Vaishnav
A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or f…