Seokil Ham

5 papers · 2023–2026 · 5 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

AAAI (1) ACL (1) CVPR (1) ECCV (1) NeurIPS (1)

Top co-authors

Changick Kim (4) Sangmin Woo (3) Hyojun Go (2) Jin-Young Kim (2) Byeongjun Park (2) Dong-Jun Han (1) Jungwuk Park (1) Seungju Cho (1) Hee-Seon Kim (1) Jungmin Son (1)

Research topics

Deep Learning (3) Machine Learning (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Learning Types · Machine Learning (2) Computer Vision (1) Architectures (1) Generation (1) Learning Types · Deep Learning (1) Models (1) Techniques (1)

Keywords

adversarial robustness (1) image generation (1) model robustness (1) knowledge distillation (1) adversarial training (1) model adaptation (1) prompt learning (1) safety alignment (1) early exit (1) state space model (1) diffusion model (1) mamba architecture (1) parameter-efficient fine-tuning (1) parameter efficiency (1) refusal behavior (1) jailbreak detection (1) mixture of prompt (1) multi-exit neural network (1) model patching (1) reverse denoising (1)

Papers

FinHarmBench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation ACL 2026 Diffusion Model Patching via Mixture-of-Prompts AAAI 2025 Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation CVPR 2025 Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts ECCV 2024 NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks NeurIPS 2023