Seokil Ham

According to our database, Seokil Ham authored at least 6 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Refusal-Feature-guided Teacher for Safe Finetuning via Data Filtering and Alignment Distillation.

Seokil Ham, Yubin Choi, Seungju Cho, Yujin Yang, Younghun Kim, Changick Kim

CoRR, June, 2025

Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation.

Seokil Ham, Hee-Seon Kim, Sangmin Woo, Changick Kim

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Diffusion Model Patching via Mixture-of-Prompts.

Seokil Ham, Sangmin Woo, Jin-Young Kim, Hyojun Go, Byeongjun Park, Changick Kim

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses.

Dong-Jun Han, Jungwuk Park, Seokil Ham, Namjin Lee, Jaekyun Moon

IEEE Trans. Neural Networks Learn. Syst., November, 2024

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts.

Byeongjun Park, Hyojun Go, Jin-Young Kim, Sangmin Woo, Seokil Ham, Changick Kim

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks.

Seokil Ham, Jungwuk Park, Dong-Jun Han, Jaekyun Moon

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023