Loom implements a 22-opcode C-compatible computer inside an 8-layer transformer with analytically derived, program-independent weights, executing instructions iteratively on a fixed-size state tensor at constant per-step cost.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
High-dimensional geometry imposes concurrency limits on semantic directions in LLM embeddings via residual interference, with N < exp(c d_eff ε²) for coexistence and σ_int ~ √(k/d_eff) for readout noise.
citing papers explorer
-
Loom: A Scalable Analytical Neural Computer Architecture
Loom implements a 22-opcode C-compatible computer inside an 8-layer transformer with analytically derived, program-independent weights, executing instructions iteratively on a fixed-size state tensor at constant per-step cost.
-
Semantic Concurrency Limits in Large Language Models
High-dimensional geometry imposes concurrency limits on semantic directions in LLM embeddings via residual interference, with N < exp(c d_eff ε²) for coexistence and σ_int ~ √(k/d_eff) for readout noise.
- Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management