keyan/te_u/result_arxiv_knowledge_graph.json

[
  {
    "name": "S,o,l,v,i,n,g, ,P,o,w,e,r, ,G,r,i,d, ,O,p,t,i,m,i,z,a,t,i,o,n, ,P,r,o,b,l,e,m,s, ,w,i,t,h, ,R,y,d,b,e,r,g, ,A,t,o,m,s",
    "authors": "Nora Bauer,K\u00fcbra Yeter-Aydeniz,Elias Kokkas,George Siopsis",
    "affiliations": "no",
    "abstract": "The rapid development of neutral atom quantum hardware provides a unique opportunity to design hardware-centered algorithms for solving real-world problems aimed at establishing quantum utility. In this work, we study the performance of two such algorithms on solving MaxCut problem for various weighted graphs. The first method uses a state-of-the-art machine learning tool to optimize the pulse shape and embedding of the graph using an adiabatic Ansatz to find the ground state. We tested the performance of this method on finding maximum power section task of the IEEE 9-bus power system and obtaining MaxCut of randomly generated problems of size up to 12 on the Aquila quantum processor. To the best of our knowledge, this work presents the first MaxCut results on Quera's Aquila quantum hardware. Our experiments run on Aquila demonstrate that even though the probability of obtaining the solution is reduced, one can still solve the MaxCut problem on cloud-accessed neutral atom quantum hardware. The second method uses local detuning, which is an emergent update on the Aquila hardware, to obtain a near exact realization of the standard QAOA Ansatz with similar performance. Finally, we study the fidelity throughout the time evolution realized in the adiabatic method as a benchmark for the IEEE 9-bus power grid graph state."
  },
  {
    "name": "T,o,w,a,r,d,s, ,H,u,m,a,n, ,A,w,a,r,e,n,e,s,s, ,i,n, ,R,o,b,o,t, ,T,a,s,k, ,P,l,a,n,n,i,n,g, ,w,i,t,h, ,L,a,r,g,e, ,L,a,n,g,u,a,g,e, ,M,o,d,e,l,s",
    "authors": "Yuchen Liu,Luigi Palmieri,Sebastian Koch,Ilche Georgievski,Marco Aiello",
    "affiliations": "no",
    "abstract": "The recent breakthroughs in the research on Large Language Models (LLMs) have triggered a transformation across several research domains. Notably, the integration of LLMs has greatly enhanced performance in robot Task And Motion Planning (TAMP). However, previous approaches often neglect the consideration of dynamic environments, i.e., the presence of dynamic objects such as humans. In this paper, we propose a novel approach to address this gap by incorporating human awareness into LLM-based robot task planning. To obtain an effective representation of the dynamic environment, our approach integrates humans' information into a hierarchical scene graph. To ensure the plan's executability, we leverage LLMs to ground the environmental topology and actionable knowledge into formal planning language. Most importantly, we use LLMs to predict future human activities and plan tasks for the robot considering the predictions. Our contribution facilitates the development of integrating human awareness into LLM-driven robot task planning, and paves the way for proactive robot decision-making in dynamic environments."
  },
  {
    "name": "E,E,G,_,G,L,T,-,N,e,t,:, ,O,p,t,i,m,i,s,i,n,g, ,E,E,G, ,G,r,a,p,h,s, ,f,o,r, ,R,e,a,l,-,t,i,m,e, ,M,o,t,o,r, ,I,m,a,g,e,r,y, ,S,i,g,n,a,l,s, ,C,l,a,s,s,i,f,i,c,a,t,i,o,n",
    "authors": "Htoo Wai Aung,Jiao Jiao Li,Yang An,Steven W. Su",
    "affiliations": "no",
    "abstract": "Brain-Computer Interfaces connect the brain to external control devices, necessitating the accurate translation of brain signals such as from electroencephalography (EEG) into executable commands. Graph Neural Networks (GCN) have been increasingly applied for classifying EEG Motor Imagery signals, primarily because they incorporates the spatial relationships among EEG channels, resulting in improved accuracy over traditional convolutional methods. Recent advances by GCNs-Net in real-time EEG MI signal classification utilised Pearson Coefficient Correlation (PCC) for constructing adjacency matrices, yielding significant results on the PhysioNet dataset. Our paper introduces the EEG Graph Lottery Ticket (EEG_GLT) algorithm, an innovative technique for constructing adjacency matrices for EEG channels. It does not require pre-existing knowledge of inter-channel relationships, and it can be tailored to suit both individual subjects and GCN model architectures. Our findings demonstrated that the PCC method outperformed the Geodesic approach by 9.65% in mean accuracy, while our EEG_GLT matrix consistently exceeded the performance of the PCC method by a mean accuracy of 13.39%. Also, we found that the construction of the adjacency matrix significantly influenced accuracy, to a greater extent than GCN model configurations. A basic GCN configuration utilising our EEG_GLT matrix exceeded the performance of even the most complex GCN setup with a PCC matrix in average accuracy. Our EEG_GLT method also reduced MACs by up to 97% compared to the PCC method, while maintaining or enhancing accuracy. In conclusion, the EEG_GLT algorithm marks a breakthrough in the development of optimal adjacency matrices, effectively boosting both computational accuracy and efficiency, making it well-suited for real-time classification of EEG MI signals that demand intensive computational resources."
  },
  {
    "name": "G,r,a,p,h, ,C,o,n,t,i,n,u,a,l, ,L,e,a,r,n,i,n,g, ,w,i,t,h, ,D,e,b,i,a,s,e,d, ,L,o,s,s,l,e,s,s, ,M,e,m,o,r,y, ,R,e,p,l,a,y",
    "authors": "Chaoxi Niu,Guansong Pang,Ling Chen",
    "affiliations": "no",
    "abstract": "Real-life graph data often expands continually, rendering the learning of graph neural networks (GNNs) on static graph data impractical. Graph continual learning (GCL) tackles this problem by continually adapting GNNs to the expanded graph of the current task while maintaining the performance over the graph of previous tasks. Memory replay-based methods, which aim to replay data of previous tasks when learning new tasks, have been explored as one principled approach to mitigate the forgetting of the knowledge learned from the previous tasks. In this paper we extend this methodology with a novel framework, called Debiased Lossless Memory replay (DeLoMe). Unlike existing methods that sample nodes/edges of previous graphs to construct the memory, DeLoMe learns small lossless synthetic node representations as the memory. The learned memory can not only preserve the graph data privacy but also capture the holistic graph information, for which the sampling-based methods are not viable. Further, prior methods suffer from bias toward the current task due to the data imbalance between the classes in the memory data and the current data. A debiased GCL loss function is devised in DeLoMe to effectively alleviate this bias. Extensive experiments on four graph datasets show the effectiveness of DeLoMe under both class- and task-incremental learning settings."
  },
  {
    "name": "N,e,u,r,o,m,o,r,p,h,i,c, ,V,i,s,i,o,n,-,b,a,s,e,d, ,M,o,t,i,o,n, ,S,e,g,m,e,n,t,a,t,i,o,n, ,w,i,t,h, ,G,r,a,p,h, ,T,r,a,n,s,f,o,r,m,e,r, ,N,e,u,r,a,l, ,N,e,t,w,o,r,k",
    "authors": "Yusra Alkendi,Rana Azzam,Sajid Javed,Lakmal Seneviratne,Yahya Zweiri",
    "affiliations": "no",
    "abstract": "Moving object segmentation is critical to interpret scene dynamics for robotic navigation systems in challenging environments. Neuromorphic vision sensors are tailored for motion perception due to their asynchronous nature, high temporal resolution, and reduced power consumption. However, their unconventional output requires novel perception paradigms to leverage their spatially sparse and temporally dense nature. In this work, we propose a novel event-based motion segmentation algorithm using a Graph Transformer Neural Network, dubbed GTNN. Our proposed algorithm processes event streams as 3D graphs by a series of nonlinear transformations to unveil local and global spatiotemporal correlations between events. Based on these correlations, events belonging to moving objects are segmented from the background without prior knowledge of the dynamic scene geometry. The algorithm is trained on publicly available datasets including MOD, EV-IMO, and \\textcolor{black}{EV-IMO2} using the proposed training scheme to facilitate efficient training on extensive datasets. Moreover, we introduce the Dynamic Object Mask-aware Event Labeling (DOMEL) approach for generating approximate ground-truth labels for event-based motion segmentation datasets. We use DOMEL to label our own recorded Event dataset for Motion Segmentation (EMS-DOMEL), which we release to the public for further research and benchmarking. Rigorous experiments are conducted on several unseen publicly-available datasets where the results revealed that GTNN outperforms state-of-the-art methods in the presence of dynamic background variations, motion patterns, and multiple dynamic objects with varying sizes and velocities. GTNN achieves significant performance gains with an average increase of 9.4% and 4.5% in terms of motion segmentation accuracy (IoU%) and detection rate (DR%), respectively."
  }
]