Training-Free Transformer Merging via Sequential Local Operator Alignment

arXiv:2610.06415 · cs.LG · Submitted 2026-10-05 · Read on arXiv

cs.LG

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/eleutherai/lm-evaluation-harness

Project page: https://akansh12.github.io/SLOA-Merge

Terminology

• Alignment — 1× in this paper · explained in 1 episode
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• On the Opportunities and Risks of Foundation Models
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• Multi-Task Learning with Deep Neural Networks: A Survey
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
• An Overview of Multi-Task Learning in Deep Neural Networks
• FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
• Symmetry in Neural Network Parameter Spaces
• Instruction-Following Evaluation for Large Language 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