English
Related papers

Related papers: Accelerating Mobile Language Model via Speculative…

200 papers

Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft model to more quickly…

Computation and Language · Computer Science 2024-10-24 Bradley McDanel

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Zihua Wang , Ruibo Li , Haozhe Du , Joey Tianyi Zhou , Yu Zhang , Xu Yang

Retrieval-Augmented Generation (RAG) has become a robust framework for enhancing Large Language Models (LLMs) with external knowledge. Recent advances in RAG have investigated graph based retrieval for intricate reasoning; however, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Tejas Sarnaik , Manan Shah , Ravi Hegde

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…

Computation and Language · Computer Science 2025-11-14 Bo Li , Zhenghua Xu , Rui Xie

With the increasing computational capability of mobile devices, deploying agentic retrieval-augmented generation (RAG) locally on heterogeneous System-on-Chips (SoCs) has become a promising way to enhance LLM-based applications. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-03 Maoliang Li , Jiayu Chen , Zihao Zheng , Ziqian Li , Xinhao Sun , Guojie Luo , Chenchen Liu , Xiang Chen

Recent advances in Retrieval-Augmented Generation (RAG) have revolutionized knowledge-intensive tasks, yet traditional RAG methods struggle when the search space is unknown or when documents are semi-structured or structured. We introduce a…

Information Retrieval · Computer Science 2026-03-25 Manie Tadayon , Mayank Gupta

The sprint-based iterative approach in the Agile software development method allows continuous feedback and adaptation. One of the crucial Agile software development activities is the sprint planning session where developers estimate the…

Software Engineering · Computer Science 2026-04-07 Lamyea Maha , Tajmilur Rahman , Chanchal Roy

With the increasing number of mobile devices, there has been continuous research on generating optimized Language Models (LMs) for soft keyboard. In spite of advances in this domain, building a single LM for low-end feature phones as well…

Computation and Language · Computer Science 2021-01-12 Sharmila Mani , Sourabh Vasant Gothe , Sourav Ghosh , Ajay Kumar Mishra , Prakhar Kulshreshtha , Bhargavi M , Muthu Kumaran

Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is…

Information Retrieval · Computer Science 2026-04-28 Minghan Li , Junjie Zou , Xinxuan Lv , Chao Zhang , Guodong Zhou

We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacrificing distributional correctness. SRT exploits the…

Machine Learning · Computer Science 2026-01-15 Chi-Chih Chang , Siqi Zhu , Zhichen Zeng , Haibin Lin , Jiaxuan You , Mohamed S. Abdelfattah , Ziheng Jiang , Xuehai Qian

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xuan Shen , Weize Ma , Yufa Zhou , Enhao Tang , Yanyue Xie , Zhengang Li , Yifan Gong , Quanyi Wang , Henghui Ding , Yiwei Wang , Yanzhi Wang , Pu Zhao , Jun Lin , Jiuxiang Gu

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We observe that for…

Machine Learning · Computer Science 2025-05-20 Qiuyu Zhu , Liang Zhang , Qianxiong Xu , Cheng Long , Jie Zhang

Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft…

Information Theory · Computer Science 2026-04-24 Yaodan Xu , Sheng Zhou , Zhisheng Niu

The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs. However,…

Neural and Evolutionary Computing · Computer Science 2025-07-15 Nan Yin , Mengzhu Wang , Zhenghan Chen , Giulia De Masi , Bin Gu , Huan Xiong

Natural Language Processing (NLP) inference is seeing increasing adoption by mobile applications, where on-device inference is desirable for crucially preserving user data privacy and avoiding network roundtrips. Yet, the unprecedented size…

Machine Learning · Computer Science 2023-02-01 Liwei Guo , Wonkyo Choe , Felix Xiaozhu Lin

Many mobile applications have been developed to apply deep learning for video analytics. Although these advanced deep learning models can provide us with better results, they also suffer from the high computational overhead which means…

Networking and Internet Architecture · Computer Science 2020-01-14 Tianxiang Tan , Guohong Cao

The research interest in specialized hardware accelerators for deep neural networks (DNN) spikes recently owing to their superior performance and efficiency. However, today's DNN accelerators primarily focus on accelerating specific…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-11 Cong Guo , Yangjie Zhou , Jingwen Leng , Yuhao Zhu , Zidong Du , Quan Chen , Chao Li , Bin Yao , Minyi Guo

Modern machine learning workloads use large models, with complex structures, that are very expensive to execute. The devices that execute complex models are becoming increasingly heterogeneous as we see a flourishing of domain-specific…

Machine Learning · Computer Science 2020-11-02 Jakub Tarnawski , Amar Phanishayee , Nikhil R. Devanur , Divya Mahajan , Fanny Nina Paravecino

Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-06-14 Wenqi Shi , Sheng Zhou , Zhisheng Niu , Miao Jiang , Lu Geng

Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines…

Information Retrieval · Computer Science 2025-08-26 Mandeep Rathee , V Venktesh , Sean MacAvaney , Avishek Anand