×-shaped variable-width transformers outperform parameter-matched uniform baselines on language modeling loss with 22% fewer FLOPs and 15% smaller KV cache.
Optimal Degrees of Synaptic Connectivity
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Coarse wiring statistics set the dynamical regime while precise connections set activity geometry in a parameter-free model of the complete larval Drosophila connectome.
Four axioms (Causality, Minimality, Separability, Stability) are formalized for latent thought representations; audits of open LLMs on 23 tasks show none satisfy all four and representations add little beyond input embeddings.
citing papers explorer
-
Variable-Width Transformers
×-shaped variable-width transformers outperform parameter-matched uniform baselines on language modeling loss with 22% fewer FLOPs and 15% smaller KV cache.
-
Separating wiring-specific from statistical control of dynamics in a complete connectome
Coarse wiring statistics set the dynamical regime while precise connections set activity geometry in a parameter-free model of the complete larval Drosophila connectome.
-
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
Four axioms (Causality, Minimality, Separability, Stability) are formalized for latent thought representations; audits of open LLMs on 23 tasks show none satisfy all four and representations add little beyond input embeddings.
- Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks