Search Results for author:
Found 17 papers, 11 papers with code
Towards LLM-Centric Multimodal Fusion: A Survey on Integration Strategies and Techniques
First, we examine architectural strategies for modality integration.
Benchmark for Antibody Binding Affinity Maturation and Design
Unlike existing antibody evaluation strategies that rely on antibody alone and its similarity to natural ones (e. g., amino acid identity rate, structural RMSD), AbBiBench considers an antibody-antigen (Ab-Ag) complex as a functional unit and evaluates the potential of an antibody design binding to given antigen by measuring protein model's likelihood on the Ab-Ag complex.
Subgraph Federated Learning for Local Generalization
In contrast, our proposed method, FedLoG, effectively tackles this issue by mitigating local overfitting.
3rd Workshop on Maritime Computer Vision (MaCVi) 2025: Challenge Results
The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater.
SoccerNet 2024 Challenges Results
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team.
MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction
MART is a hypergraph transformer architecture to consider individual and group behaviors in transformer machinery.
M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition
Therefore, we propose multi-scale patch selection (MSPS) to improve the multi-scale capabilities of existing ViT-based models.
Does ChatGPT Comprehend the Place Value in Numbers When Solving Math Word Problems?
Based on the observation that CoT tends to yield lower accuracy than PoT when large numbers are involved, we conducted two experiments to examine whether chatGPT understands place values in numbers.
Ranked #7 on
Math Word Problem Solving
on SVAMP
Task-Equivariant Graph Few-shot Learning
To solve this problem, it is important for GNNs to be able to classify nodes with a limited number of labeled nodes, known as few-shot node classification.
Conditional Graph Information Bottleneck for Molecular Relational Learning
Molecular relational learning, whose goal is to learn the interaction behavior between molecular pairs, got a surge of interest in molecular sciences due to its wide range of applications.
Heterogeneous Graph Learning for Multi-modal Medical Data Analysis
In this paper, we propose an effective graph-based framework called HetMed (Heterogeneous Graph Learning for Multi-modal Medical Data Analysis) for fusing the multi-modal medical data.
Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition
Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images.
Relational Self-Supervised Learning on Graphs
Despite their success, existing GRL methods tend to overlook an inherent distinction between images and graphs, i. e., images are assumed to be independently and identically distributed, whereas graphs exhibit relational information among data instances, i. e., nodes.
GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment
Despite the success of Graph Neural Networks (GNNs) on various applications, GNNs encounter significant performance degradation when the amount of supervision signals, i. e., number of labeled nodes, is limited, which is expected as GNNs are trained solely based on the supervision obtained from the labeled nodes.
Augmentation-Free Self-Supervised Learning on Graphs
Inspired by the recent success of self-supervised methods applied on images, self-supervised learning on graph structured data has seen rapid growth especially centered on augmentation-based contrastive methods.
Automatic Detection of Injection and Press Mold Parts on 2D Drawing Using Deep Neural Network
This paper proposes a method to automatically detect the key feature parts in a CAD of commercial TV and monitor using a deep neural network.
Multiple Classification with Split Learning
We divided a single deep learning architecture into a common extractor, a cloud model and a local classifier for the distributed learning.
