Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/KellerJordan/Muon
Sources
- Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
- S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner
- LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
- PIQA: Reasoning about Physical Commonsense in Natural Language
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Post-Optimization Adaptive Rank Allocation for LoRA
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- CSULoRA: Closest Safe Update Low-Rank Adaptation
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
- Parameter Efficient Fine-tuning via Explained Variance Adaptation
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- LoRA vs Full Fine-tuning: An Illusion of Equivalence
- Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting
- Magicoder: Empowering Code Generation with OSS-Instruct
- The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning
- Qwen3 Technical Report
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