arXiv:2510. 19366v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs).
arXiv:2606. 27743v1 Announce Type: cross Abstract: Large Language Models (LLMs) inference is typically deployed under a static resource assumption, where models execute a fixed computational graph regardless of the runtime environment.
arXiv:2608.28726v1 Announce Type: new Abstract: The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant chal...
arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.
arXiv:2609.23085v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajector...
arXiv:2603. 16867v2 Announce Type: replace Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment.
arXiv:2606. 09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale.
arXiv:2602. 06154v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully.
arXiv:2606. 03770v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become integral to modern applications, yet their deployment remains challenging.
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.
S2-MoE is a self‑speculative decoding framework designed to make Mixture‑of‑Experts (MoE) inference more efficient on edge devices. It reduces verification overhead by using routing‑aware adaptive speculative expansion, improves verification efficiency with reuse‑aware expert gating, and aligns draft and target execution through shared context. Implemented in llama.cpp, S2‑MoE delivers up to 5.3× speedup (≈2.0× on average) over standard autoregressive decoding across various MoE models and datasets on edge hardware.
arXiv:2607. 24787v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator memory.