Dongwoo Kim

In-Place Feedback: A New Paradigm for Guiding Large Language Models in Multi-Turn Reasoning

Generalization Bound for GNNs on Transductive Node Classification: A View from Optimal Transport

The Oversmoothing Fallacy: A Misguided Narrative in GNN Research

High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction

Influence Functions for Edge Edits in Non-Convex Graph Neural Networks

Towards Bridging Generalization and Expressivity of Graph Neural Networks

Posterior Label Smoothing for Node Classification

Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization

Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning

Taming Gradient Oversmoothing and Expansion in Graph Neural Networks