7 papers
VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)
Canyang Wu, Jinrong Zhang, Xusheng He +3
Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides strong promptable mask propagati…
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
Haolong Chen, Liang Zhang, Zhuo Li +2
While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evol…
STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction
Haolong Chen, Liang Zhang, Zhengyuan Xin +1
Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term spatio-temporal dependencies eff…
DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks
Qizhe Li, Haolong Chen, Jiansheng Li +7
Diagnosing the root causes of Quality of Experience (QoE) degradations in operational mobile networks is challenging due to complex cross-layer interactions among kernel performanc…
An overview of domain-specific foundation model: key technologies, applications and challenges
Haolong Chen, Hanzhi Chen, Zijian Zhao +6
The impressive performance of ChatGPT and other foundation-model-based products in human language understanding has prompted both academia and industry to explore how these models…
FeedSign: Robust Full-parameter Federated Fine-tuning of Large Models with Extremely Low Communication Overhead of One Bit
Zhijie Cai, Haolong Chen, Guangxu Zhu
Federated fine-tuning (FFT) attempts to fine-tune a pre-trained model with private data from distributed clients by exchanging models rather than data under the orchestration of a…