How Language Models Differ in Redistributing Attention-Head Activity Under Serial Demand
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/johnnyjli/serial-demand-heads
Sources
- Do Language Models Use Their Depth Efficiently?
- The Llama 3 Herd of Models
- Mistral 7B
- The Remarkable Robustness of LLMs: Stages of Inference?
- Qwen2.5 Technical Report
- 2 OLMo 2 Furious
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks