When Can Attention Heads Be Statically Defined?

arXiv:2609.34650 · cs.LG, cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/waylonli/Selective-Attention-Freezing

Terminology

• Pruning — 84× in this paper · explained in 4 episodes
• Calibration — 48× in this paper · explained in 7 episodes
• Perplexity — 45× in this paper · explained in 3 episodes
• Accuracy — 43× in this paper · explained in 1 episode
• Adaptation — 24× in this paper · explained in 1 episode
• Benchmark — 18× in this paper · explained in 2 episodes
• Transformer — 12× in this paper · explained in 2 episodes
• Redundancy — 5× in this paper · explained in 2 episodes
• Reconstruction Error — 4× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Selective Attention Freezing — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Activation Checkpointing — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• FreezeOut: Accelerate Training by Progressively Freezing Layers
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer
• The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
• Input-independent Attention Weights Are Expressive Enough: A Study of Attention in Self-supervised Audio Transformers

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