English
Related papers

Related papers: LLM Router: Rethinking Routing with Prefill Activa…

200 papers

Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet user-specific cost-performance trade-offs. However, existing…

Computation and Language · Computer Science 2026-04-13 Hui Liu , Bin Zou , Kecheng Chen , Jie Liu , Wenya Wang , Haoliang Li

Large language models (LLMs) have achieved success, but cost and privacy constraints necessitate deploying smaller models locally while offloading complex queries to cloud-based models. Existing router evaluations are unsystematic,…

Computation and Language · Computer Science 2026-02-13 Wanxing Wu , He Zhu , Yixia Li , Lei Yang , Jiehui Zhao , Hongru Wang , Jian Yang , Benyou Wang , Bingyi Jing , Guanhua Chen

Masked language modelling (MLM) as a pretraining objective has been widely adopted in genomic sequence modelling. While pretrained models can successfully serve as encoders for various downstream tasks, the distribution shift between…

Machine Learning · Computer Science 2025-02-26 Monireh Safari , Pablo Millan Arias , Scott C. Lowe , Lila Kari , Angel X. Chang , Graham W. Taylor

LLM routing aims to achieve a favorable quality--cost trade-off by dynamically assigning easy queries to smaller models and harder queries to stronger ones. However, across both unimodal and multimodal settings, we uncover a pervasive yet…

Artificial Intelligence · Computer Science 2026-02-04 Guannan Lai , Han-Jia Ye

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing…

Machine Learning · Computer Science 2025-05-13 Hang Wu , Jianian Zhu , Yinghui Li , Haojie Wang , Biao Hou , Jidong Zhai

Mixture-of-Experts (MoE) architectures have become the key to scaling modern LLMs, yet little is understood about how their sparse routing dynamics respond to multilingual data. In this work, we analyze expert routing patterns using…

Computation and Language · Computer Science 2026-02-19 Lucas Bandarkar , Chenyuan Yang , Mohsen Fayyaz , Junlin Hu , Nanyun Peng

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training…

Artificial Intelligence · Computer Science 2026-05-26 Yifan Zeng , Yiran Wu , Yaolun Zhang , Wentian Zhao , Kun Wan , Qingyun Wu , Huazheng Wang

Prefill-Decode (P/D) disaggregation has emerged as a widely adopted optimization strategy for Large Language Model (LLM) inference. However, there currently exists no well-established methodology for determining the optimal number of P/D…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-06 Luchang Li , Dongfang Li , Bozhao Gong , Yu Zhang

The rapid advancements in large language models (LLMs) have led to the emergence of routing techniques, which aim to efficiently select the optimal LLM from diverse candidates to tackle specific tasks, optimizing performance while reducing…

Computation and Language · Computer Science 2025-09-25 Ruihan Jin , Pengpeng Shao , Zhengqi Wen , Jinyang Wu , Mingkuan Feng , Shuai Zhang , Jianhua Tao

Masked diffusion language models (MDLMs) are trained to in-fill positions in randomly masked sequences, in contrast to next-token prediction models. Discussions around MDLMs focus on two benefits: (1) any-order decoding and 2) multi-token…

Machine Learning · Computer Science 2025-10-24 Zachary Horvitz , Raghav Singhal , Hao Zou , Carles Domingo-Enrich , Zhou Yu , Rajesh Ranganath , Kathleen McKeown

The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…

Machine Learning · Computer Science 2025-12-01 Jungyeon Koh , Hyun Jong Yang

Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also incurs significant costs in inference latency and token…

Emerging Technologies · Computer Science 2025-10-13 Chen Wang , Xunzhuo Liu , Yuhan Liu , Yue Zhu , Xiangxi Mo , Junchen Jiang , Huamin Chen

Fine-tuning pre-trained large language models (LLMs) in a distributed manner poses significant challenges on resource-constrained edge networks. To address this challenge, we propose SflLLM, a novel framework that integrates split federated…

Machine Learning · Computer Science 2025-07-03 Kai Zhao , Zhaohui Yang , Ye Hu , Mingzhe Chen , Chen Zhu , Zhaoyang Zhang

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense…

Computation and Language · Computer Science 2023-06-21 Kun Zhou , Xiao Liu , Yeyun Gong , Wayne Xin Zhao , Daxin Jiang , Nan Duan , Ji-Rong Wen

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contain latent semantic parallelism--decomposable structures where…

Machine Learning · Computer Science 2025-10-22 Steven Kolawole , Keshav Santhanam , Virginia Smith , Pratiksha Thaker

We show that MLP layers in transformer language models perform binary routing of continuous signals: the decision of whether a token needs nonlinear processing is well-captured by binary neuron activations, even though the signals being…

Machine Learning · Computer Science 2026-03-12 Peter Balogh

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Computation and Language · Computer Science 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

LLM routers aim to balance quality and cost of generation by classifying queries and routing them to a cheaper or more expensive LLM depending on their complexity. Routers represent one type of what we call LLM control planes: systems that…

Cryptography and Security · Computer Science 2025-01-06 Avital Shafran , Roei Schuster , Thomas Ristenpart , Vitaly Shmatikov

Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overlooked optimization issue in multi-layer feature fusion. Skip…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Ziye Yuan , Ruchang Yao , Chengxin Zheng , Yusheng Zhao , Daxiang Dong , Ming Zhang