# ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models

arXiv: https://arxiv.org/abs/2610.01296 · HTML: https://mlsanity.com/paper/2610.01296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 39 of its 47 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)
- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)
- Efficient LLM inference and serving / [Diffusion LLM and MoE inference](https://mlsanity.com/inference/diffusion-llm-and-moe-inference/)

## Builds on (most cited first, 30 of 39)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints](https://mlsanity.com/paper/2212.05055/) (2022)
- [SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation](https://mlsanity.com/paper/2510.06303/) (2025)
- [Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing](https://mlsanity.com/paper/2508.09192/) (2025)
- [Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models](https://mlsanity.com/paper/2509.23653/) (2025)
- [MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance](https://mlsanity.com/paper/2505.03804/) (2025)
- [Delta Decompression for MoE-based LLMs Compression](https://mlsanity.com/paper/2502.17298/) (2025)
- [Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts](https://mlsanity.com/paper/2403.09176/) (2024)
- [Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget](https://mlsanity.com/paper/2407.15811/) (2024)
- [EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing](https://mlsanity.com/paper/2410.02098/) (2024)
- [MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design](https://mlsanity.com/paper/2505.05799/) (2025)
- [Learning Unmasking Policies for Diffusion Language Models](https://mlsanity.com/paper/2512.09106/) (2025)
- [DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning](https://mlsanity.com/paper/2509.16105/) (2025)
- [Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance](https://mlsanity.com/paper/2510.24711/) (2025)
- [Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline](https://mlsanity.com/paper/2502.06888/) (2025)
- [Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation](https://mlsanity.com/paper/2510.09094/) (2025)
- [Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts](https://mlsanity.com/paper/2503.16057/) (2025)
- [MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE](https://mlsanity.com/paper/2507.00390/) (2025)
- [Mixture of Lookup Experts](https://mlsanity.com/paper/2503.15798/) (2025)

## Abstract (arXiv)

Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs substantial computation and storage costs. Existing low-rank MoE compression methods largely rely on static factorization and fixed rank allocation, which overlook the distinctive properties of MoE DLMs. Specifically, we identify two properties: cross-mode non-uniform redundancy, where parameter redundancy and sensitivity to rank truncation vary across the input, output, and expert modes, and token-wise utilization variation, where hot and cold tokens exhibit distinct spectral characteristics and expert activation patterns. To address these challenges, we propose ITC-MoE, an Importance-guided Token-aware Compression framework for MoE DLMs. ITC-MoE consists of two complementary components. First, Importance-guided Adaptive Tucker Compression (IATC) incorporates activation and gradient importance into expert weight transformation, jointly factorizes expert weights across multiple modes, and adaptively allocates ranks under a fixed parameter budget. Second, Token-aware Compensation and Routing (TCR) applies lightweight low-rank compensation to compression-sensitive hot tokens and restricts the candidate expert set for cold tokens with concentrated routing patterns. By jointly adapting compression capacity and inference execution to both parameter redundancy and token-wise variation, ITC-MoE substantially reduces the computation and storage costs of MoE DLMs while preserving their generation quality. For example, on SDAR-30B-A3B-Chat-b32, ITC-MoE maintains an accuracy of 96.33% on MultiArith under a 30% compression budget, while achieving up to a 7.22x end-to-end speedup. The code is publicly available at https://github.com/lianjunl13-sudo/ITC-MoE.