Compute Aligned Training: Optimizing for Test Time Inference

arXiv:2604.24957 · cs.LG, cs.AI · Submitted 2026-04-27 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-04-27

Updated: 2026-09-30

Code: https://github.com/adamoosya/compute-aligned-training

Terminology

• Loss Function — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Supervised Fine-Tuning — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• Scaling Laws for Neural Language Models
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
• Mistral 7B
• Measuring Mathematical Problem Solving With the MATH Dataset
• Scaling Test-Time Compute for Agentic Coding
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Maximum Entropy RL (Provably) Solves Some Robust RL Problems
• Omnipredictors

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