2 citations · 4 across the 21 of their papers we have counts for
25 papers
Reflection with Action-Induced Visual Differences for Desktop GUI Agents
Yijie Ma, Chaoyue Niu, Fan Wu +1
The Planner-Operator-Reflector (POR) framework is widely used in GUI agents to maintain objective alignment in complex tasks through modular collaboration. However, desktop GUIs in…
Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs
Zhihao Xu, Hao Zhong, Zeting Zhou +9
This paper aims to enable computation- and communication-efficient GPU sharing across devices within local area networks (LANs), facilitating ubiquitous AI inference on heterogeneo…
CKV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
Chuheng Du, Junyi Chen, Hanlin Tang +7
Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inf…
BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
Yuhang Xu, Kaibin Tian, Yang Tian +6
Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency…
Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM
Hang Zeng, Xiangyu Liu, Yong Hu +5
Personal intelligence requires strong capabilities under strict privacy and efficiency constraints. Unlike cloud-first intelligence, which relies on powerful but costly and privacy…
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
Jiarui Zhang, Xiangyu Liu, Yong Hu +5
Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maxim…
SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
Chenzhi Hu, Qinzhe Hu, Yuhang Xu +6
Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths. However, the inherent v…
Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion
Yumou Liu, Zhenzhe Zheng, Jiang Rong +3
Modern content platforms offer paid promotion to mitigate cold start by allocating exposure via auctions. Our empirical analysis reveals a counterintuitive flaw in this paradigm: w…
CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
Gucongcong Fan, Chaoyue Niu, Chengfei Lyu +2
Mobile agents rely on Large Language Models (LLMs) to plan and execute tasks on smartphone user interfaces (UIs). While cloud-based LLMs achieve high task accuracy, they require up…
Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps
Chen Gong, Yan Zhuang, Zhenzhe Zheng +4
Machine learning (ML) models are increasingly integrated into modern mobile apps to enable personalized and intelligent services. These models typically rely on rich input features…
TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling
Junyi Chen, Chuheng Du, Renyuan Liu +6
Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i…
Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization
Yuhang Xu, Shengzhong Liu, Dong Zhang +3
This paper presents Nova, a real-time scheduling framework for serving agentic vision-language models (VLMs) on a single GPU with balanced per-request latency and overall request p…
ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
Bonan Zhang, Zhongqi Chen, Bowen Song +3
Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with…
MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection
Zhengxiang Huang, Chaoyue Niu, Zhaode Wang +8
As the demand for on-device Large Language Model (LLM) inference grows, energy efficiency has become a major concern, especially for battery-limited mobile devices. Our analysis sh…
Pre: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation
Junyi Chen, Shihao Bai, Zaijun Wang +7
Extensive LLM applications demand efficient structured generations, particularly for LR(1) grammars, to produce outputs in specified formats (e.g., JSON). Existing methods primaril…
RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
Jiarui Zhang, Xiangyu Liu, Yong Hu +3
Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across L…
Automated Privacy Information Annotation in Large Language Model Interactions
Hang Zeng, Xiangyu Liu, Yong Hu +4
Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their…
Responsive DNN Adaptation for Video Analytics against Environment Shift via Hierarchical Mobile-Cloud Collaborations
Maozhe Zhao, Shengzhong Liu, Fan Wu +1
Mobile video analysis systems often encounter various deploying environments, where environment shifts present greater demands for responsiveness in adaptations of deployed "expert…
ABO: Abandon Bayer Filter for Adaptive Edge Offloading in Responsive Augmented Reality
Yongxuan Han, Shengzhong Liu, Fan Wu +1
Bayer-patterned color filter array (CFA) has been the go-to solution for color image sensors. In augmented reality (AR), although color interpolation (i.e., demosaicing) of pre-dem…
Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions
Chaoyue Niu, Yucheng Ding, Junhui Lu +7
The conventional cloud-based large model learning framework is increasingly constrained by latency, cost, personalization, and privacy concerns. In this survey, we explore an emerg…
Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance
Shangyu Liu, Zhenzhe Zheng, Xiaoyao Huang +3
Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented g…
Personalized Language Model Learning on Text Data Without User Identifiers
Yucheng Ding, Yangwenjian Tan, Xiangyu Liu +6
In many practical natural language applications, user data are highly sensitive, requiring anonymous uploads of text data from mobile devices to the cloud without user identifiers.…
Personalized LLM for Generating Customized Responses to the Same Query from Different Users
Hang Zeng, Chaoyue Niu, Fan Wu +2
Existing work on large language model (LLM) personalization assigned different responding roles to LLMs, but overlooked the diversity of queriers. In this work, we propose a new fo…
Adaptive Routing of Text-to-Image Generation Requests Between Large Cloud Model and Light-Weight Edge Model
Zewei Xin, Qinya Li, Chaoyue Niu +2
Large text-to-image models demonstrate impressive generation capabilities; however, their substantial size necessitates expensive cloud servers for deployment. Conversely, light-we…