SEONGHWAN KIM

4 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ICLR (2) ACL (1) NeurIPS (1)

Top co-authors

Woo Youn Kim (3) Seokhyun Moon (2) Jun Hyeong Kim (2) Jeheon Woo (2) Joongbo Shin (1) Dongkyu Lee (1) Honglak Lee (1) Stanley Jungkyu Choi (1) Seonghyun Park (1) Hyeonsu Kim (1)

Research topics

Deep Learning (4) Machine Learning (3) Artificial Intelligence (2) Architectures (2) Core AI (2) Core Methods (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Models (2) Optimization & Theory (2) Interdisciplinary (1) Application Areas (1) Science (1)

Keywords

molecular optimization (1) metric learning (1) optimal transport (1) mutual information (1) markov chain (1) training efficiency (1) quantum chemistry (1) molecular dynamics (1) schrödinger bridge (1) discrete diffusion (1) off-policy training (1) amortized sampling (1) 3d geometry (1) molecular property prediction (1) transition path sampling (1) negative mining (1) siamese network (1) hard negative sampling (1) graph transformation (1) graph neural network (1)

Papers

Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation ICLR 2025 Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers ICLR 2025 Efficient Dynamic Hard Negative Sampling for Dialogue Selection ACL 2024 GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising NeurIPS 2023