12 papers
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,…
Generation Quality-Latency Tradeoff-Aware Inference Offloading for Multimodal LLMs in Cloud-Edge Continuum
Zhongxiao Wang, Yueshen Xu, Xinkui Zhao +2
Beyond pure cloud, some efforts are being made to deploy Large Language Models (LLMs) in edge to accelerate inference response. So the deployment of LLMs in cloud-edge continuum be…
Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving
Haoxin Liu, Jiayi Wang, Yueshen Xu +1
As large language models (LLMs) are increasingly deployed with highly heterogeneous workloads, chunked-prefill execution has emerged as a mainstream serving architecture. Balancing…
ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy
Xinkui Zhao, Sai Liu, Yifan Zhang +6
Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle wi…
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…
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-…
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…
TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models
Xinkui Zhao, Haode Li, Yifan Zhang +2
Recent advances in large language models (LLMs) have unlocked powerful reasoning and decision-making capabilities. However, their inherent dependence on static parametric memory fu…
StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
Xinkui Zhao, Yifan Zhang, Zhengyi Zhou +1
Recent advances in large language models (LLMs) have substantially enhanced automated code generation across a wide range of programming languages. Nonetheless, verifying the corre…
DRAMA: Next-Gen Dynamic Orchestration for Resilient Multi-Agent Ecosystems in Flux
Xinkui Zhao, Yifan Zhang, Sai Liu +6
Multi-agent systems (MAS) have demonstrated significant effectiveness in addressing complex problems through coordinated collaboration among heterogeneous agents. However, real-wor…
LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead
Yifan Zhang, Xinkui Zhao, Zuxin Wang +4
The rapid advancement of large language models has unlocked remarkable capabilities across a diverse array of natural language processing tasks. However, the considerable differenc…
Next-Gen Computing Systems with Compute Express Link: a Comprehensive Survey
Chen Chen, Xinkui Zhao, Guanjie Cheng +3
Interconnection is crucial for computing systems. However, the current interconnection performance between processors and devices, such as memory devices and accelerators, signific…