Beyond Expert Rankings: Contrast Calibration for Mixed-Precision MoE Quantization

arXiv:2610.20353 · cs.LG, stat.ML · Submitted 2026-10-14 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 26 pages, including references and appendices

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 1× in this paper · explained in 9 episodes
• Quantization — 1× in this paper · explained in 15 episodes

Sources

• MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
• GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
• Model Compression with Exact Budget Constraints via Riemannian Manifolds
• Mixtral of Experts
• Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs
• Pointer Sentinel Mixture Models
• FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification
• AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization

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