MoRE: Scaling mixture of experts with hardware-aware low-rank routing

arXiv:2609.36301 · cs.LG, cs.AI, cs.CL, stat.ML · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.AI, cs.CL, stat.ML

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/Matheart/MoRE_code

Terminology

• Perplexity — 23× in this paper · explained in 3 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Embeddings — 7× in this paper · explained in 2 episodes
• Scaling Laws — 7× in this paper · explained in 4 episodes
• Sparsity — 7× in this paper · explained in 4 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Decode — 6× in this paper · explained in 2 episodes
• Mixture of Experts — 5× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• High Bandwidth Memory — 2× in this paper
• Mixture of Rank-reduced-routed Experts — 2× in this paper
• Mixture-of-Experts (MoE) — 2× in this paper · explained in 7 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes

Sources

• Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
• Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
• Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
• Memory Layers at Scale
• Secret mixtures of experts inside your LLM
• Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
• On the Representation Collapse of Sparse Mixture of Experts
• Unified Scaling Laws for Routed Language Models
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Memorizing Gaussians with no over-parameterizaion via gradient decent on neural networks
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• DeepSeek-V3 Technical Report
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
• SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
• LoRA+: Efficient Low Rank Adaptation of Large Models
• ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling
• Mixture of A Million Experts
• Liger Kernel: Efficient Triton Kernels for LLM Training
• LoRA: Low-Rank Adaptation of Large Language Models
• Ultra-Sparse Memory Network

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