Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- Training Large Language Models to Reason in a Continuous Latent Space
- Training Language Models to Self-Correct via Reinforcement Learning
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
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