Scholar
Minseon Kim
Google Scholar ID: ZwObZNwAAAAJ
Microsoft Research
Citations & Impact
Citations
734
H-index
8
i10-index
8
Publications
20
Co-authors
27
list available
Publications
Resume (English only)
Academic Achievements
- Published 'BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing' at NeurIPS 2025
- Published 'Learning to Solve Complex Problems via Dataset Decomposition' at NeurIPS 2025
- Published 'Rethinking Safety in LLM Fine-tuning: An Optimization Perspective' at CoLM 2025
- Published 'Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts' at CoLM 2025
- Published 'Medical Red Teaming Protocol of Language Models: On the Importance of User Perspectives in Healthcare Settings' on arXiv 2025
- Published 'Instilling Parallel Reasoning into Language Models' at ICML AI for Math WS 2025
- Published 'Enhancing Variational Autoencoders with Smooth Robust Latent Encoding' on arXiv 2025
- Published 'debug-gym: A Text-Based Environment for Interactive Debugging' on arXiv 2025
- Published 'Automatic Jailbreaking of the Text-to-Image Generative AI Systems' at ICML Safety WS 2024
- Published 'Optimizing Query Generation for Enhanced Document Retrieval in RAG' on arXiv 2024
- Published 'Protein Representation Learning by Capturing Protein Sequence‑Structure‑Function Relationship' at ICLR MLGenX WS 2024 (Spotlight)
- Published 'Effective Targeted Attacks for Adversarial Self‑Supervised Learning' at NeurIPS 2023
- Published 'Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations' at NeurIPS 2023
- Published 'Language Detoxification with Attribute‑Discriminative Latent Space' at ACL 2023
- Published 'Context‑dependent Instruction Tuning for Dialogue Response Generation' on arXiv 2023
- Published 'Meta‑Prediction Model for Distillation‑aware NAS on Unseen Datasets' at ICLR 2023 (Spotlight)
- Published 'Rethinking the Entropy of Instance in Adversarial Training' at IEEE SaTML 2023
- Published 'Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation' at AutoML WS 2022
- Published 'Learning Transferable Adversarial Robust Representations via Multi‑view Consistency' at NeurIPS SafetyML WS 2022
- Published 'Consistency Regularization for Adversarial Robustness' at AAAI 2022
- Published 'MRI‑based classification of neuropsychiatric systemic lupus erythematosus patients with self‑supervised contrastive learning' in Frontiers in Neuroscience 2022
- Published 'Adversarial Self‑Supervised Contrastive Learning' at NeurIPS 2020
- Organized WiML @ CoLM 2025 event
- Gave a talk at the MSR × Mila Workshop titled 'Learning to Extract Context for Context-aware LLM Inference.'
