12 accepted papers
Graph Neural Networks (GNNs) have emerged as powerful tools for learning on graph-structured data, but often struggle to balance local and global information. While graph Transformers aim to address this by enabling long-range interactions, they often overlook the inherent locality and efficiency of
Accurate focus quality assessment (FQA) in fluorescence microscopy is challenging due to stain-dependent optical variations that induce heterogeneous focus behavior across images. Existing methods, however, treat focus quality as a stain-agnostic problem, assuming a shared global ordering. We formul
Finding the optimal configuration of Sparse Mixture-of- Experts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frameworks either heavily rely on hyperparameter tuning or overlook the importance
Linear attention reformulates sequence modeling as recurrent state evolution, enabling efficient linear-time inference. Under the key–value associative paradigm, existing approaches restrict the role of the query to the readout operation, decoupling it from state evolution. We show that query-condit…
Mixture-of-Experts (MoE) scales model capacity efficiently by selectively routing inputs to a specialized subset of experts. However, input-expert specialization, the core motivation of MoE, critically depends on whether the router is actually aware of input structure. In practice, MoE routing is ty…
Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using Supervised Fine-Tuning (SFT). However, SFT datasets are ofte…
Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), whic…
Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts…
This letter proposes the Polygon-based Random Tree search algorithm with Variable polygon size (PRT-V) for Variable Topology Truss (VTT). This algorithm improves on our previous path planning algorithm by using VTT’s ability to change its size drastically. The algorithm partitions the space into unc
This letter proposes the use of a polygon-based random tree path planning algorithm for a variable geometry topology system (VGT). By combining a path planning algorithm and our previous non-impact locomotion algorithm, the proposed VGT system reaches an objective point. The proposed path planning a
In this letter, an active ball joint actuator, called the master node, is developed for the purpose of reconfiguring truss structures. We propose a variable topology truss system, which is an advanced variable geometry truss system that can reconfigure its own topology to expand its functions. Howev
A variable geometry truss (VGT) is a modular truss-structured robot consisting of linear actuators and three-degree-of-freedom joints. Having a sophisticated structure, the VGT can easily be damaged when it rolls and impacts the ground. This letter proposes a nonimpact rolling locomotion scheme to a