1 citations · 1 across the 21 of their papers we have counts for
22 papers
Measurement-Driven Diagnosis and Mitigation of Host-CPU Co-location Interference in Single-GPU LLM Serving on a Multi-GPU Server
Guanjie Cheng, Guowei Li, Yingying Wen +3
Host CPUs in GPU servers are often under-used during LLM inference. Co-locating CPU workloads can improve resource use, but it can also seriously hurt serving quality. Existing wor…
Prediction-Robust Service Deployment with Capacity-Aware Edge Admission
Hailiang Zhao, Ziqi Wang, Yifei Zhang +4
Edge platforms instantiate executable services close to users to reduce request-serving cost, but each instance incurs a one-time deployment cost and remains useful only for a fini…
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
Xinkui Zhao, Enbo Chen, Yifan Zhang +4
Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However,…
FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs
Yifan Zhang, Xinkui Zhao, Sai Liu +3
Large language model (LLM) agents autonomously interleave semantic reasoning with complex system operations. In these dynamic environments, static tool-level permissions are fundam…
SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction
Zhaopeng Feng, Chen Zhi, Xuhong Zhang +2
Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. However, existing methods typic…
ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
Xinkui Zhao, Sai Liu, Yifan Zhang +4
The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this coll…
TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training
Guanjie Cheng, Boyi Li, Lingyu Sun +4
Large-scale multimodal pre-trained models like CLIP rely heavily on high-quality training data, yet raw web-crawled datasets are often noisy, misaligned, and redundant, leading to…
Shiva-DiT: Residual-Based Differentiable Top- Selection for Efficient Diffusion Transformers
Jiaji Zhang, Hailiang Zhao, Jiaju Wu +3
Diffusion Transformers (DiTs) are costly at high resolution because self-attention scales quadratically with token sequence length. Existing pruning methods do not jointly provide…
Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection
Zhiwei Ling, Hailiang Zhao, Chao Zhang +8
Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes while preserving data privacy, making it a cornerstone of intelligent serv…
Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression
Jianping Zhong, Guochang Li, Chen Zhi +6
Large Language Models (LLMs) struggle with long-context code due to window limitations. Existing textual code compression methods mitigate this via selective filtering but often di…
Better Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code Completion
Baoyi Wang, Xingliang Wang, Guochang Li +6
Repository-level code completion remains challenging for large language models (LLMs) due to cross-file dependencies and limited context windows. Prior work addresses this challeng…
Industrial Data-Service-Knowledge Governance: Toward Integrated and Trusted Intelligence
Hailiang Zhao, Ziqi Wang, Daojiang Hu +9
The convergence of artificial intelligence, cyber-physical systems, and distributed networking has accelerated the evolution of industrial intelligence across edge, cloud, and cros…
Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding
Xinkui Zhao, Zuxin Wang, Yifan Zhang +6
The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and descr…
TenonOS: A Self-Generating LibOS-on-LibOS Framework for Time-Critical Embedded Operating Systems
Xinkui Zhao, Yifan Zhang, Haidan Zhao +7
The growing complexity of embedded systems creates tension between rich functionality and strict resource and real-time constraints. Traditional monolithic operating system and hyp…
Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding
Xinkui Zhao, Rongkai Liu, Yifan Zhang +6
As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-…
Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
Ziying Li, Xuequan Lu, Xinkui Zhao +3
Recent advancements in optimization-based text-to-3D generation heavily rely on distilling knowledge from pre-trained text-to-image diffusion models using techniques like Score Dis…
LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping
Guanjie Cheng, Mengzhen Yang, Xinkui Zhao +5
Federated learning (FL) enables collaborative model training across distributed nodes without exposing raw data, but its decentralized nature makes it vulnerable in trust-deficient…
MUSE: A Heterogeneity-Aware Multimedia Search Engine for Mobile SoCs
Xinkui Zhao, Qingyu Ma, Yifan Zhang +6
On-device multimedia retrieval is vital for smartphones, enabling applications like cross-modal semantic search and multimodal personal AI agents. However, realizing efficient retr…
ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing
Guanjie Cheng, Siyang Liu, Xinkui Zhao +4
Mobile edge crowdsensing (MECS) enables large-scale real-time sensing services, but its continuous data collection and transmission pipeline exposes terminal devices to dynamic pri…
SatFusion: A Unified Framework for Enhancing Remote Sensing Images via Multi-Frame and Multi-Source Images Fusion
Yufei Tong, Guanjie Cheng, Peihan Wu +3
High-quality remote sensing (RS) image acquisition is fundamentally constrained by physical limitations. While Multi-Frame Super-Resolution (MFSR) and Pansharpening address this by…
Reliable Microservice Tail Latency Prediction via Decoupled Dual-Stream Learning and Gradient Modulation
Wenzhuo Qian, Hailiang Zhao, Jiayi Chen +7
Microservice architectures enable scalable cloud-native applications; however, the distributed nature of these systems complicates the maintenance of strict Service Level Objective…
Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning
Ping Li, Tao Wang, Xinkui Zhao +2
Video captioning generate a sentence that describes the video content. Existing methods always require a number of captions (\eg, 10 or 20) per video to train the model, which is q…