8 papers
Automating and Scaling Behavioral Scientific Research on AI Agents
Soo Yong Lee, Jongha Lee, Jaewan Chun +7
As AI agents are increasingly deployed in complex environments, understanding their behaviors becomes critical. Yet behavioral scientific research on AI agents remains manual and l…
View Space: Learning Representation across Arbitrary Graphs
Dooho Lee, Myeong Kong, Minho Jeong +1
Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive inference on numerical data is parti…
ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation
Sunwoo Kim, Geon Lee, Kyungho Kim +2
Recently, large language models (LLMs) have been widely used as recommender systems, owing to their reasoning capability and effectiveness in handling cold-start items. A common ap…
Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
Sunwoo Kim, Soo Yong Lee, Kyungho Kim +3
Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information…
Emergence of psychopathological computations in large language models
Soo Yong Lee, Hyunjin Hwang, Taekwan Kim +5
Can large language models (LLMs) instantiate computations of psychopathology? An effective approach to the question hinges on addressing two factors. First, for conceptual validity…
'Hello, World!': Making GNNs Talk with LLMs
Sunwoo Kim, Soo Yong Lee, Jaemin Yoo +1
While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In t…