Supervised fine-tuning (SFT) is the de facto standard for adapting large language models (LLMs) to target domains, but it often degrades the model's general capabilities, a phenomenon known as catastr...
arXiv:2601. 05106v5 Announce Type: replace Abstract: Large language models (LLMs) exhibit strengths across diverse domains.
arXiv:2606. 10338v1 Announce Type: cross Abstract: Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored.
ACE introduces a training‑free, calibration‑free framework for adaptive expert skipping in Mixture‑of‑Experts LLMs. It combines a Global Spectral Proxy that estimates global transformation capacity with a Router‑Conditioned Refinement that builds expert‑specific direction prototypes, enabling the model to skip low‑contribution experts while always keeping the top‑1 expert. Offline computation of expert statistics leaves only lightweight table lookups during inference, and experiments on three MoE‑based LLMs show ACE outperforms static and dynamic baselines, especially at high skipping ratios.
arXiv:2606. 06098v1 Announce Type: cross Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialized tasks via domain-expert LLMs.
The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.
arXiv:2607. 08780v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices.
arXiv:2608. 06396v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models route each token through a small subset of experts, making routing patterns useful for identifying task-relevant experts during downstream adaptation.
The paper introduces Skill Schema Transport (SST), a post‑training framework that mitigates catastrophic forgetting in continual domain adaptation by translating new domain knowledge into a model’s existing skill space. SST abstracts each example type into a reusable skill schema, preserving essential operations while removing domain‑specific surface forms, thereby turning knowledge updates into procedural reuse rather than trajectory memorization. Experiments on two 3B instruction‑tuned backbones show that SST consistently reduces forgetting and improves generalization, achieving up to a 5.75‑point performance gain and a dramatic drop in maximum forgetting from 42.41 to 7.10 points on the Qwen‑3B MATH stream.
The paper studies how the design of Mixture-of-Experts (MoE) routers affects inference speed when combined with Speculative Decoding (SD). It shows that routers promoting high expert coactivation reduce memory transfer costs and improve runtime. By integrating a global load‑balancing loss, shared experts, a consistency loss, and an autoregressive expert selection mechanism, the authors achieve a 21% throughput gain over baseline MoEs while preserving accuracy.
arXiv:2607. 08991v1 Announce Type: new Abstract: Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality.
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...