Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras

arXiv:2609.01129 · cs.LG · Submitted 2026-09-01 · Read on arXiv

cs.LG

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Core — 16× in this paper · explained in 2 episodes
• Transformer — 15× in this paper · explained in 2 episodes
• In-Context Learning — 3× in this paper · explained in 4 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits
• Mistral 7B
• In-context Learning and Induction Heads
• Qwen2.5 Technical Report
• 2 OLMo 2 Furious
• The Communication Map of a Transformer
• Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel
• Qwen3 Technical Report
• TinyLlama: An Open-Source Small Language Model

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks