NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
arXiv preprint arXiv:2505.11581 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones.
citing papers explorer
-
Gradient-Based Program Synthesis with Neurally Interpreted Languages
NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
-
Characterizing Universal Object Representations Across Vision Models
Vision models converge on universal object dimensions that are semantically interpretable and align more closely with biological vision than model-specific ones.
- Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale