3 citations · 13 across the 18 of their papers we have counts for
23 papers
EdgeCraft: Automated Model Crafting for Edge IoT
Genglin Wang, Kaiwei Liu, Liekang Zeng +4
Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific scenario requires navigating…
CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion
Genglin Wang, Wangsong Yin, Yeerzhati Abudunuer +3
Multi-document retrieval-augmented generation (RAG) requires a language model to process multiple retrieved text chunks before answering a question. Precomputing each chunk's KV ca…
SkillVine: Agent Skill Evolution via Branching Exploration
Kaiwei Liu, Jiqian Dong, Liran Dong +7
Agent skills encapsulate reusable procedural knowledge that enables LLM agents to perform tasks, and they can be improved automatically using trajectories from interactions with th…
ProAssist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks
Lilin Xu, Bufang Yang, Siyang Jiang +6
Procedural tasks with multiple ordered steps are ubiquitous in daily life. Recent advances in multimodal large language models (MLLMs) have enabled personal assistants that support…
SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams
Bufang Yang, Lilin Xu, Yixuan Li +3
Personalization is essential for Large Language Model (LLM)-based agents to adapt to users' preferences and improve response quality and task performance. However, most existing ap…
PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices
Kaiwei Liu, Liekang Zeng, Lilin Xu +2
Retrieval-augmented generation (RAG) has become a de facto paradigm in various large language model (LLM)-driven applications on mobile devices, such as mobile assistants leveragin…
A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
Siyang Jiang, Mu Yuan, Xiang Ji +12
Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable de…
VibOmni: Towards Scalable Bone-conduction Speech Enhancement on Earables
Lixing He, Yunqi Guo, Haozheng Hou +1
Earables, such as True Wireless Stereo earphones and VR/AR headsets, are increasingly popular, yet their compact design poses challenges for robust voice-related applications like…
DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals
Kaiwei Liu, Yuting He, Bufang Yang +6
Biosignals collected from wearable devices are widely utilized in healthcare applications. Machine learning models used in these applications often rely on features extracted from…
ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
Bufang Yang, Lilin Xu, Liekang Zeng +8
Recent studies have begun to explore proactive large language model (LLM) agents that provide unobtrusive assistance by automatically leveraging contextual information, such as in…
Synera: Synergistic LLM Serving across Device and Cloud at Scale
Genglin Wang, Liekang Zeng, Bufang Yang +6
Large Language Models (LLMs) are becoming key components in various mobile operating systems, driving smart applications like interactive chatbots and personal assistants. While br…
An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding
Siyang Jiang, Bufang Yang, Lilin Xu +8
The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device hu…
CoHear: Conversation Enhancement via Multi-Earphone Collaboration
Lixing He, Yunqi Guo, Zhenyu Yan +1
In crowded places such as conferences, background noise, overlapping voices, and lively interactions make it difficult to have clear conversations. This situation often worsens the…
ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
Bufang Yang, Lilin Xu, Liekang Zeng +7
Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either re…
EgoLog: Ego-Centric Fine-Grained Daily Log with Ubiquitous Wearables
Lixing He, Bufang Yang, Di Duan +2
Despite advances in human activity recognition (HAR) with different modalities, a precise, robust, and accurate daily log system is not yet available. Current solutions primarily r…
MMLNB: Multi-Modal Learning for Neuroblastoma Subtyping Classification Assisted with Textual Description Generation
Huangwei Chen, Yifei Chen, Zhenyu Yan +4
Neuroblastoma (NB), a leading cause of childhood cancer mortality, exhibits significant histopathological variability, necessitating precise subtyping for accurate prognosis and tr…
SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions
Bufang Yang, Yunqi Guo, Lilin Xu +4
Social interactions are fundamental to human life. The recent emergence of large language models (LLMs)-based virtual assistants has demonstrated their potential to revolutionize h…
Visualizing the Invisible: A Generative AR System for Intuitive Multi-Modal Sensor Data Presentation
Yunqi Guo, Kaiyuan Hou, Heming Fu +4
Understanding sensor data can be difficult for non-experts because of the complexity and different semantic meanings of sensor modalities. This leads to a need for intuitive and ef…
DrHouse: An LLM-empowered Diagnostic Reasoning System through Harnessing Outcomes from Sensor Data and Expert Knowledge
Bufang Yang, Siyang Jiang, Lilin Xu +6
Large language models (LLMs) have the potential to transform digital healthcare, as evidenced by recent advances in LLM-based virtual doctors. However, current approaches rely on p…
Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving
Shuyao Shi, Neiwen Ling, Zhehao Jiang +9
Recently,smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore the potential of infrastructure-assisted auton…
VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments
Bufang Yang, Lixing He, Kaiwei Liu +1
Individuals with visual impairments, encompassing both partial and total difficulties in visual perception, are referred to as visually impaired (VI) people. An estimated 2.2 billi…
EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge
Bufang Yang, Lixing He, Neiwen Ling +5
Deep Learning (DL) models have been widely deployed on IoT devices with the help of advancements in DL algorithms and chips. However, the limited resources of edge devices make the…
ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer's Disease
Xiaomin Ouyang, Xian Shuai, Yang Li +12
Alzheimer's Disease (AD) and related dementia are a growing global health challenge due to the aging population. In this paper, we present ADMarker, the first end-to-end system tha…