MeqMuon: Matrix-Equilibrating Muon for LLM Pretraining
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- Evaluating Large Language Models Trained on Code
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Training Compute-Optimal Large Language Models
- Kimi K2: Open Agentic Intelligence
- Kimi K3: Open Frontier Intelligence
- The Power of Normalization: Faster Evasion of Saddle Points
- DeepSeek-V3 Technical Report
- Muon is Scalable for LLM Training
- DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen2 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