8 citations · 10 across the 6 of their papers we have counts for
7 papers
Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
Soyeon Kim, Kyowoon Lee, Jaesik Choi
Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to inpu…
Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution
Soyeon Kim, Seongwoo Lim, Kyowoon Lee +1
Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield…
K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology
Soyeon Kim, Cheongwoong Kang, Myeongjin Lee +3
The development of practical (multimodal) large language model assistants for Korean weather forecasters is hindered by the absence of a multidimensional, expert-level evaluation f…
Example-Based Concept Analysis Framework for Deep Weather Forecast Models
Soyeon Kim, Junho Choi, Subeen Lee +1
To improve the trustworthiness of an AI model, finding consistent, understandable representations of its inference process is essential. This understanding is particularly importan…
Explainable AI-Based Interface System for Weather Forecasting Model
Soyeon Kim, Junho Choi, Yeji Choi +6
Machine learning (ML) is becoming increasingly popular in meteorological decision-making. Although the literature on explainable artificial intelligence (XAI) is growing steadily,…
Diverse Rare Sample Generation with Pretrained GANs
Subeen Lee, Jiyeon Han, Soyeon Kim +1
Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and th…
Capsule Neural Networks as Noise Stabilizer for Time Series Data
Soyeon Kim, Jihyeon Seong, Hyunkyung Han +1
Capsule Neural Networks utilize capsules, which bind neurons into a single vector and learn position equivariant features, which makes them more robust than original Convolutional…