In a vignette study of 354 U.S. participants, deletion-based privacy controls outperformed all other controls in increasing willingness to engage with GenAI chatbots for emotional support, while technically complex controls like local-only processing and model training opt-outs reduced engagement.
hub
On-device language models: A comprehensive review.arXiv preprint arXiv:2409.00088
27 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
27
Pith papers citing it
3
external citations · Pith
abstract
The advent of large language models (LLMs) revolutionized natural language processing applications, and running LLMs on edge devices has become increasingly attractive for reasons including reduced latency, data localization, and personalized user experiences. This comprehensive review examines the challenges of deploying computationally expensive LLMs on resource-constrained devices and explores innovative solutions across multiple domains. The paper investigates the development of on-device language models, their efficient architectures, including parameter sharing and modular designs, as well as state-of-the-art compression techniques like quantization, pruning, and knowledge distillation. Hardware acceleration strategies and collaborative edge-cloud deployment approaches are analyzed, highlighting the intricate balance between performance and resource utilization. Case studies of on-device language models from major mobile manufacturers demonstrate real-world applications and potential benefits. The review also addresses critical aspects such as adaptive learning, multi-modal capabilities, and personalization. By identifying key research directions and open challenges, this paper provides a roadmap for future advancements in on-device language models, emphasizing the need for interdisciplinary efforts to realize the full potential of ubiquitous, intelligent computing while ensuring responsible and ethical deployment. For a comprehensive review of research work and educational resources on on-device large language models (LLMs), please visit https://github.com/NexaAI/Awesome-LLMs-on-device. To download and run on-device LLMs, visit https://www.nexaai.com/models.
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
FlexServe introduces recallable secure memory and NPU to enable cooperative secure LLM inference on mobile devices, reporting 10.05X TTFT speedup over a basic TrustZone strawman.
WISV uses a channel-aware semantic acceptance policy on hidden representations to boost accepted sequence length by up to 60.8% and cut interaction rounds by 37.3% in distributed speculative decoding, with under 1% accuracy loss.
Page-granular Flex-Mem and switchable Flex-NPU cut TrustZone LLM TTFT by ~10× vs a CMA strawman and ~2.4× vs a pipelined secure-NPU strawman on RK3588.
Benign multilingual fine-tuning causes language-specific safety drifts with adversarial compliance rates rising up to four-fold, decoupled from capability gains.
First end-to-end RAG on mobile NPU delivers 18.1x faster prefilling, 4x lower latency and energy than CPU on Snapdragon X Elite with equivalent quality.
Interview study of 44 novice researchers finds privacy fears paradoxically accelerate LLM use for faster publication, with misconceptions about idea value and data dilution, and perceived ineffective mitigations.
An LLM-orchestrated physics simulation search identifies polymers with strong insulin interactions, outperforming standard optimization methods by significant margins.
ScrapMem reports SOTA 51.0% Joint@10 on ATM-Bench with up to 93% memory reduction and 70.3% Recall@10 via optical forgetting and EM-Graph.
Reference-augmented offline policy optimization through a differentiable RNN dynamics model cuts TDCR tip-position error by ~51% versus non-augmented training and outperforms Jacobian controllers across speeds.
A new benchmark shows LLM smartphone agents achieve comparable success with screen text alone as with screenshots, but both fail often due to UI accessibility and reasoning gaps.
CoreQ delivers adaptive mismatch correction via closed-form geometric coefficient and successive rounding to improve PTQ accuracy for large language models.
AgentProg reframes interaction history as a program with variables and control flow, plus a belief state for partial observability, achieving SOTA success rates on long-horizon GUI benchmarks while baselines degrade.
A net-value-per-byte curator governs memory lifecycle in on-device LLM agents, cutting memory 2.7x and uplink 2.4x while driving injection success to zero on task-drift benchmarks and Jetson hardware.
WEQA proposes a query-adaptive agent framework combining LLMs with wearable data tools, achieving 24% higher accuracy than baselines on a benchmark from four open datasets, with gains in expert-rated usefulness.
Personal agents require edge deployment to preserve high-fidelity local context and zero-latency loops, as claimed through three structural shifts away from cloud-centric designs.
An LLM-based framework recommends drill-down paths in visual analytics by approximating a greedy algorithm, interpreting user intent, and managing exploration branches to reduce cognitive load.
Fog and LLMs are mutual beneficiaries: quantization and related optimizations enable SLMs on fog devices, while LLM code generation can automate TOSCA-style dynamic fog application deployment.
RecGPT-Mobile runs a compact LLM on phones to understand evolving user intent from behaviors and improve mobile e-commerce recommendations.
A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while supporting user-driven Delta adjustments.
Corpus scaling in RAG frequently matches the accuracy gains from larger LLMs on open-domain QA tasks, with mid-sized models benefiting most due to better passage coverage.
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
This research agenda argues that cloud-native architectures, microservices, autoscaling, and emerging trends like serverless inference and federated learning are required to make large language models efficient and scalable.
citing papers explorer
-
The Impact of Security and Privacy Controls on Users' Emotional Engagement with Generative AI Chatbots
In a vignette study of 354 U.S. participants, deletion-based privacy controls outperformed all other controls in increasing willingness to engage with GenAI chatbots for emotional support, while technically complex controls like local-only processing and model training opt-outs reduced engagement.
-
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
FlexServe introduces recallable secure memory and NPU to enable cooperative secure LLM inference on mobile devices, reporting 10.05X TTFT speedup over a basic TrustZone strawman.
-
WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference
WISV uses a channel-aware semantic acceptance policy on hidden representations to boost accepted sequence length by up to 60.8% and cut interaction rounds by 37.3% in distributed speculative decoding, with under 1% accuracy loss.
-
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
Page-granular Flex-Mem and switchable Flex-NPU cut TrustZone LLM TTFT by ~10× vs a CMA strawman and ~2.4× vs a pipelined secure-NPU strawman on RK3588.
-
The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
Benign multilingual fine-tuning causes language-specific safety drifts with adversarial compliance rates rising up to four-fold, decoupled from capability gains.
-
Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite
First end-to-end RAG on mobile NPU delivers 18.1x faster prefilling, 4x lower latency and energy than CPU on Snapdragon X Elite with equivalent quality.
-
Investigating Novice Researchers' Perceptions of Research Privacy Within LLM-Assisted Workflows
Interview study of 44 novice researchers finds privacy fears paradoxically accelerate LLM use for faster publication, with misconceptions about idea value and data dilution, and perceived ineffective mitigations.
-
Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
An LLM-orchestrated physics simulation search identifies polymers with strong insulin interactions, outperforming standard optimization methods by significant margins.
-
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
ScrapMem reports SOTA 51.0% Joint@10 on ATM-Bench with up to 93% memory reduction and 70.3% Recall@10 via optical forgetting and EM-Graph.
-
Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots
Reference-augmented offline policy optimization through a differentiable RNN dynamics model cuts TDCR tip-position error by ~51% versus non-augmented training and outperforms Jacobian controllers across speeds.
-
Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots
A new benchmark shows LLM smartphone agents achieve comparable success with screen text alone as with screenshots, but both fail often due to UI accessibility and reasoning gaps.
-
CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
CoreQ delivers adaptive mismatch correction via closed-form geometric coefficient and successive rounding to improve PTQ accuracy for large language models.
-
AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management
AgentProg reframes interaction history as a program with variables and control flow, plus a belief state for partial observability, achieving SOTA success rates on long-horizon GUI benchmarks while baselines degrade.
-
Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
A net-value-per-byte curator governs memory lifecycle in on-device LLM agents, cutting memory 2.7x and uplink 2.4x while driving injection success to zero on task-drift benchmarks and Jetson hardware.
-
WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning
WEQA proposes a query-adaptive agent framework combining LLMs with wearable data tools, achieving 24% higher accuracy than baselines on a benchmark from four open datasets, with gains in expert-rated usefulness.
-
Beyond Scaling: Agents Are Heading to the Edge
Personal agents require edge deployment to preserve high-fidelity local context and zero-latency loops, as claimed through three structural shifts away from cloud-centric designs.
-
Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration
An LLM-based framework recommends drill-down paths in visual analytics by approximating a greedy algorithm, interpreting user intent, and managing exploration branches to reduce cognitive load.
-
Fog Computing and Large Language Models: A vision for mutual beneficiaries
Fog and LLMs are mutual beneficiaries: quantization and related optimizations enable SLMs on fog devices, while LLM code generation can automate TOSCA-style dynamic fog application deployment.
-
RecGPT-Mobile: On-Device Large Language Models for User Intent Understanding in Taobao Feed Recommendation
RecGPT-Mobile runs a compact LLM on phones to understand evolving user intent from behaviors and improve mobile e-commerce recommendations.
-
Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while supporting user-driven Delta adjustments.
-
Less LLM, More Documents: Searching for Improved RAG
Corpus scaling in RAG frequently matches the accuracy gains from larger LLMs on open-domain QA tasks, with mid-sized models benefiting most due to better passage coverage.
-
Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
-
Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda
This research agenda argues that cloud-native architectures, microservices, autoscaling, and emerging trends like serverless inference and federated learning are required to make large language models efficient and scalable.
- SOD: Step-wise On-policy Distillation for Small Language Model Agents
- NVLLM: A 3D NAND-Centric Architecture Enabling Edge on-Device LLM Inference
- Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
- Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs