37 citations · 189 across the 24 of their papers we have counts for
25 papers
PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud
Chenghua Wang, Daliang Xu, Dongqi Cai +23
Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Altho…
Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution
Zhiyang Chen, Daliang Xu, Haiyang Shen +5
Performing Retrieval-Augmented Generation (RAG) directly on mobile devices is promising for data privacy and responsiveness but is hindered by the architectural constraints of mobi…
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
Yunhe Yan, Shihe Wang, Jiajun Du +12
(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GU…
MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs
Zhenyan Lu, Daliang Xu, Dongqi Cai +5
Large language models (LLMs) are deployed on mobile devices to power killer applications such as intelligent assistants. LLMs pre-trained on general corpora often hallucinate when…
LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
Yanan Li, Fanxu Meng, Muhan Zhang +3
As Large Language Models (LLMs) are frequently updated, LoRA weights trained on earlier versions quickly become obsolete. The conventional practice of retraining LoRA weights from…
Recall: Empowering Multimodal Embedding for Edge Devices
Dongqi Cai, Shangguang Wang, Chen Peng +2
Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding…
MobileViews: A Million-scale and Diverse Mobile GUI Dataset
Longxi Gao, Li Zhang, Shihe Wang +6
Visual language models (VLMs) empower mobile GUI agents to interpret complex mobile screens and respond to user requests. Training such capable agents requires large-scale, high-qu…
FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts
Hanzi Mei, Dongqi Cai, Ao Zhou +2
As Large Language Models (LLMs) push the boundaries of AI capabilities, their demand for data is growing. Much of this data is private and distributed across edge devices, making F…
FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
Zeling Zhang, Dongqi Cai, Yiran Zhang +3
Communication overhead is a significant bottleneck in federated learning (FL), which has been exaggerated with the increasing size of AI models. In this paper, we propose FedRDMA,…
A Survey of Resource-efficient LLM and Multimodal Foundation Models
Mengwei Xu, Wangsong Yin, Dongqi Cai +15
Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine lear…
Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
Zhichao Lu, Chuntao Ding, Shangguang Wang +3
Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interes…
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Chuntao Ding, Zhichao Lu, Shangguang Wang +2
Multi-task learning (MTL) seeks to learn a single model to accomplish multiple tasks by leveraging shared information among the tasks. Existing MTL models, however, have been known…
Mobile Foundation Model as Firmware
Jinliang Yuan, Chen Yang, Dongqi Cai +9
In today's landscape, smartphones have evolved into hubs for hosting a multitude of deep learning models aimed at local execution. A key realization driving this work is the notabl…
EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices
Rongjie Yi, Liwei Guo, Shiyun Wei +3
Large language models (LLMs) such as GPTs and Mixtral-8x7B have revolutionized machine intelligence due to their exceptional abilities in generic ML tasks. Transiting LLMs from dat…
FwdLLM: Efficient FedLLM using Forward Gradient
Mengwei Xu, Dongqi Cai, Yaozong Wu +2
Large Language Models (LLMs) are transforming the landscape of mobile intelligence. Federated Learning (FL), a method to preserve user data privacy, is often employed in fine-tunin…
TFormer: A Transmission-Friendly ViT Model for IoT Devices
Zhichao Lu, Chuntao Ding, Felix Juefei-Xu +3
Deploying high-performance vision transformer (ViT) models on ubiquitous Internet of Things (IoT) devices to provide high-quality vision services will revolutionize the way we live…
More is Different: Prototyping and Analyzing a New Form of Edge Server with Massive Mobile SoCs
Li Zhang, Zhe Fu, Boqing Shi +7
Huge energy consumption poses a significant challenge for edge clouds. In response to this, we introduce a new type of edge server, namely SoC Cluster, that orchestrates multiple l…
Federated Few-Shot Learning for Mobile NLP
Dongqi Cai, Shangguang Wang, Yaozong Wu +2
Natural language processing (NLP) sees rich mobile applications. To support various language understanding tasks, a foundation NLP model is often fine-tuned in a federated, privacy…
Towards Practical Few-shot Federated NLP
Dongqi Cai, Yaozong Wu, Haitao Yuan +3
Transformer-based pre-trained models have emerged as the predominant solution for natural language processing (NLP). Fine-tuning such pre-trained models for downstream tasks often…
Device-centric Federated Analytics At Ease
Li Zhang, Junji Qiu, Shangguang Wang +1
Nowadays, high-volume and privacy-sensitive data are generated by mobile devices, which are better to be preserved on devices and queried on demand. However, data analysts still la…
Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading
Daliang Xu, Mengwei Xu, Qipeng Wang +6
This paper proposes Mandheling, the first system that enables highly resource-efficient on-device training by orchestrating the mixed-precision training with on-chip Digital Signal…
Accelerating Vertical Federated Learning
Dongqi Cai, Tao Fan, Yan Kang +4
Privacy, security and data governance constraints rule out a brute force process in the integration of cross-silo data, which inherits the development of the Internet of Things. Fe…
Boosting DNN Cold Inference on Edge Devices
Rongjie Yi, Ting Cao, Ao Zhou +3
DNNs are ubiquitous on edge devices nowadays. With its increasing importance and use cases, it's not likely to pack all DNNs into device memory and expect that each inference has b…
FedAdapter: Efficient Federated Learning for Modern NLP
Dongqi Cai, Yaozong Wu, Shangguang Wang +2
Transformer-based pre-trained models have revolutionized NLP for superior performance and generality. Fine-tuning pre-trained models for downstream tasks often requires private dat…