arXiv Computation and Language September 16, 2026 By Foivos Charalampakos, Md Ibrahim Ibne Alam, Iordanis Koutsopoulos, Koushik Kar

Optimal Model Activation Policies for Inference Networks of Large Language Models

Read the original on arXiv Computation and Language →

The Flow has not summarised this story yet — read it at arXiv Computation and Language.

arXiv AI

Jul 15

Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts

arXiv:2607. 12696v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns.

By Jincheng Xie, Runheng Liu, Heyan Huang, Yawen Ling, Hanbin Dai, Yu Zheng, Wen Hu

llms benchmarks

arXiv Machine Learning

Jun 17

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models

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.

By Nurbek Tastan, Stefanos Laskaridis, Karthik Nandakumar, Samuel Horvath

llms benchmarks

arXiv Machine Learning

Jun 5

IR3DE: A Linear Router for Large Language Models

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.

By Eros Fan\`i, O\u{g}uzhan Ersoy

llms

arXiv AI

Jul 15

Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning

arXiv:2512. 01113v2 Announce Type: replace-cross Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural networks and also for transformer models.

By Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang

llms benchmarks

arXiv Machine Learning

1d ago

Long-Context Demonstration Selection Using State Space Models

arXiv:2609.17888v1 Announce Type: new Abstract: We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This prob...

By Ziniu Zhang, Zhenshuo Zhang, Ruoxuan Xiong, Gene Cooperman, Hongyang R. Zhang

llms rag nlp efficiency

arXiv AI

Jun 10

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

arXiv:2606. 09856v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable.

By Liyi Zhang, Akshay K. Jagadish, Brenden M. Lake, Thomas L. Griffiths

llms agents fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models

IR3DE: A Linear Router for Large Language Models

Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning

Long-Context Demonstration Selection Using State Space Models

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models