Publications (25)
Spanning Triangle-trees and Flows of Graphs
Jiaao Li, Xueliang Li, Meiling Wang
In this paper we study the flow-property of graphs containing a spanning triangle-tree. Our main results provide a structure characterization of graphs with a spanning triangle-tre…
KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng
Oleg Senkevich, Siyang Xu, Tianyi Jiang +13
Approximate Nearest Neighbor Search (ANNS) is a cornerstone algorithm for information retrieval, recommendation systems, and machine learning applications. While x86-based architec…
OpenObject-NAV: Open-Vocabulary Object-Oriented Navigation Based on Dynamic Carrier-Relationship Scene Graph
Yujie Tang, Meiling Wang, Yinan Deng +3
In everyday life, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as well. As a…
Complementary Graphs with Flows Less Than Three
Jiaao Li, Xueliang Li, Meiling Wang
X. Hou, H.-J. Lai, P. Li and C.-Q. Zhang [J. Graph Theory 69 (2012) 464-470] showed that for a simple graph with , if , then either $G…
Robots Acquire Manipulation Skills in Seconds from a Single Human Video
Guangyan Chen, Meiling Wang, Te Cui +9
The ability to acquire skills rapidly and effortlessly while retaining those already mastered is essential for robots. However, current methods still rely on a cumbersome training-…
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Songhua Liu, Tianwei Lin, Dongliang He +6
Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Exist…
Advancing Cancer Prognosis with Hierarchical Fusion of Genomic, Proteomic and Pathology Imaging Data from a Systems Biology Perspective
Junjie Zhou, Bao Xue, Meiling Wang +2
To enhance the precision of cancer prognosis, recent research has increasingly focused on multimodal survival methods by integrating genomic data and histology images. However, cur…
RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management
Lingzhe Zhang, Tong Jia, Weijie Hong +9
Modern software systems operate at unprecedented scale and complexity, where effective failure management is critical yet increasingly challenging. Metrics, traces, and logs provid…
Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction
Guangyan Chen, Meiling Wang, Yufeng Yue +2
Recent Transformer-based methods have achieved advanced performance in point cloud registration by utilizing advantages of the Transformer in order-invariance and modeling dependen…
Point Tree Transformer for Point Cloud Registration
Meiling Wang, Guangyan Chen, Yi Yang +2
Point cloud registration is a fundamental task in the fields of computer vision and robotics. Recent developments in transformer-based methods have demonstrated enhanced performanc…
PointGPT: Auto-regressively Generative Pre-training from Point Clouds
Guangyan Chen, Meiling Wang, Yi Yang +3
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired…
Group Connectivity under -Edge-Connectivity
Miaomiao Han, Jiaao Li, Xueliang Li +1
Let be two distinct finite Abelian groups with . A fundamental theorem of Tutte shows that a graph admits a nowhere-zero -flow if and only if it admits a nowhere-…
Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought
Lingzhe Zhang, Tong Jia, Kangjin Wang +8
As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with rising frequency. Ensuring sys…
KBest: Efficient Vector Search on Kunpeng CPU
Kaihao Ma, Meiling Wang, Senkevich Oleg +19
Vector search, which returns the vectors most similar to a given query vector from a large vector dataset, underlies many important applications such as search, recommendation, and…
Gorgeous: Revisiting the Data Layout for Disk-Resident High-Dimensional Vector Search
Peiqi Yin, Xiao Yan, Qihui Zhou +6
Similarity-based vector search underpins many important applications, but a key challenge is processing massive vector datasets (e.g., in TBs). To reduce costs, some systems utiliz…
See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations
Guangyan Chen, Meiling Wang, Qi Shao +10
Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated pro…
Human Demonstrations are Generalizable Knowledge for Robots
Te Cui, Tianxing Zhou, Zicai Peng +6
Learning from human demonstrations is an emerging trend for designing intelligent robotic systems. However, previous methods typically regard videos as instructions, simply dividin…
OpenIN: Open-Vocabulary Instance-Oriented Navigation in Dynamic Domestic Environments
Yujie Tang, Meiling Wang, Yinan Deng +3
In daily domestic settings, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as…
DINO-CoDT: Multi-class Collaborative Detection and Tracking with Vision Foundation Models
Xunjie He, Christina Dao Wen Lee, Meiling Wang +4
Collaborative perception plays a crucial role in enhancing environmental understanding by expanding the perceptual range and improving robustness against sensor failures, which pri…
FMimic: Foundation Models are Fine-grained Action Learners from Human Videos
Guangyan Chen, Meiling Wang, Te Cui +8
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vis…
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
Guanyan Chen, Meiling Wang, Te Cui +9
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have…
AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer
Tianwei Lin, Honglin Lin, Fu Li +5
Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unreali…
Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation
Lingzhe Zhang, Tong Jia, Mingyu Wang +9
Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration…
Spin Faraday Waves in Periodically Modulated Spin-Orbit-Coupled Bose Gases
Hongguang Liang, Meiling Wang, Juan Wang +1
This paper investigates the formation of Spin Faraday waves in spin-orbit-coupled Bose-Einstein condensate under the stripe phase and explores the dispersion relation under three d…
Parametric excitations in a harmonically trapped binary Bose-Einstein condensate
Meiling Wang, Juan Wang, Yan Li +2
We investigate parametric excitation and pattern formation in a harmonically trapped two-component Bose-Einstein condensate. We assume the condensate to be in the miscible phase, b…