49 citations · 162 across the 31 of their papers we have counts for
36 papers
PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation
Zewei Xin, Qinya Li, Chaoyue Niu +1
While diffusion models achieve impressive image generation capabilities, they suffer from high computational costs, implausible artifacts, and limited adaptability to dynamic or pr…
Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs
Zhengxiang Huang, Shengheng Chen, Chaoyue Niu +6
On-device large language model (LLM) serving is a cornerstone of local-first personal intelligence, offering users data sovereignty, strong privacy guarantees, and freedom from clo…
TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing
Tianxing Wang, Mingming Zhao, Shuai Huang +4
Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed. However, such pre-execution commitment creates an orchestration bo…
ECHO: Dyadic 3D Facial Motion Generation with Asymmetric Deterministic Articulation and Stochastic Reaction
Zhuoqiang Cai, Yujie Sun, Chaoyue Niu +4
We propose ECHO for dyadic 3D facial motion generation under a strict dual-stream audio-only setting, formulating the problem as an asymmetric task involving speech-constrained art…
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…
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…
Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
Xuezhen Tu, Jingyu Wu, Fangyu Kang +4
Spatio-Temporal Video Grounding requires jointly localizing target objects across both temporal and spatial dimensions based on natural language queries, posing fundamental challen…
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…
FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Captures
Yujie Sun, Zhuoqiang Cai, Chaoyue Niu +4
We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views. Unlike previous approaches…
VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement
Tiancheng Fang, Bowen Pan, Lingxi Chen +4
We propose VIAFormer, a Voxel-Image Alignment Transformer model designed for Multi-view Conditioned Voxel Refinement--the task of repairing incomplete noisy voxels using calibrated…
HRM^2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone Scans
Chao Shi, Shenghao Jia, Jinhui Liu +6
We present HRMAvatar, a framework for creating high-fidelity avatars from monocular phone scans, which can be rendered and animated in real time on mobile devices. Monocular ca…
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…
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…
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…
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…
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…
DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models
Yucheng Ding, Chaoyue Niu, Fan Wu +3
Many large vision models have been deployed on the cloud for real-time services. Meanwhile, fresh samples are continuously generated on the served mobile device. How to leverage th…
One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design
Yikai Yan, Chaoyue Niu, Fan Wu +4
The mainstream workflow of image recognition applications is first training one global model on the cloud for a wide range of classes and then serving numerous clients, each with h…
On-Device Model Fine-Tuning with Label Correction in Recommender Systems
Yucheng Ding, Chaoyue Niu, Fan Wu +3
To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mob…
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Chengfei Lv, Chaoyue Niu, Renjie Gu +17
To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system,…