ITC-MoE introduces an Importance-guided Token-aware Compression framework for Mixture-of-Experts Diffusion Language Models. It combines Adaptive Tucker Compression, which uses activation and gradient importance to jointly factorize expert weights and allocate ranks, with Token-aware Compensation and Routing that applies low‑rank adjustments to hot tokens and limits expert candidates for cold tokens. The method achieves significant reductions in computation and storage while maintaining generation quality, exemplified by a 30% compression budget that preserves 96.33% accuracy on MultiArith and delivers up to a 7.22× speedup.
arXiv:2608. 03457v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understood.
arXiv:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...
arXiv:2510. 02345v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.
arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.
arXiv:2511. 04805v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input.
arXiv:2608. 07814v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many expert weight matrices.
arXiv:2606. 02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.
arXiv:2609.38823v1 Announce Type: new Abstract: Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly becau...
arXiv:2606. 15453v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost.
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
ExFold is a training‑free expert‑folding framework that jointly accelerates the prefill and decode phases of Mixture‑of‑Experts (MoE) models by projecting the contributions of excluded experts onto a retained expert set using calibrated scalar projectors. It treats both phases as a budgeted output‑approximation problem, achieving token‑level Top‑K folding for prefill and batch‑level expert‑pool folding for decode. Implemented as a plug‑and‑play plugin in vLLM with a lightweight CUDA kernel, ExFold delivers up to 1.41× TTFT and 2.45× TPOT speedups while preserving about 99% of the original model quality.
arXiv:2606. 31796v1 Announce Type: cross Abstract: We study three complementary techniques for training compute-efficient language models.