Evaluating Trajectory Features for Routing Final-Layer Attention

cs.LG, cs.AI

Submitted: 2026-10-07

Updated: 2026-10-07

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Trajectory Dynamics in Language Model Hidden States Predict Human Processing Costs Beyond Surprisal
• Compressive Transformers for Long-Range Sequence Modelling
• Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
• When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models

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