Seonghwan Park 박성환

• Aug 2026

  Our paper on recovering black-box 3D models from pose shifts was accepted to WACV 2027 (Round 1).

• Jun 2026

  Our papers on efficient OOD detection and monocular avatar reconstruction were accepted to ECCV 2026.

• Jan 2026

  Joined the Korea Electronics Technology Institute (KETI) as a researcher, working on 3D vision and physical AI under Dr. Min-Gyu Park.

• Sep 2025

  Our paper on robust concept bottleneck models was accepted to NeurIPS 2025.

• Aug 2025

  Completed my M.S. in AI at POSTECH, advised by Prof. Namhoon Lee.

• Jan 2025

  Our paper on black-box prompt tuning was accepted to ICLR 2025.

• Jun 2024

  Started a project with Samsung Advanced Institute of Technology (SAIT) on visual prompting for MMFM-based VQA.

• Jun 2023

  Our paper on backprop-free federated learning was presented at the ICML 2023 Federated Learning Workshop.

• Mar 2023

  Started my M.S. in AI at POSTECH, joining the Computational Optimization Lab under Prof. Namhoon Lee.

• Recovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization

  Seonghwan Park, Min-Gyu Park

  WACV 2027Accepted as a Round 1 paper

  3D VisionRobustnessOptimization

• Exploiting Local Flatness for Efficient Out-of-Distribution Detection

  Seonghwan Park, Hyunji Jung, Dongyeop Lee, Namhoon Lee

  ECCV 2026

  RobustnessEfficiency

• JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video

  Changyeon Won, Min-Gyu Park, Seonghwan Park, Ju Hong Yoon, Hae-Gon Jeon

  ECCV 2026

  3D VisionOptimization

• An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations

  Seonghwan Park, Jueun Mun, Donghyun Oh, Namhoon Lee

  NeurIPS 2025

  InterpretabilityRobustnessOptimization

• ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models

  Seonghwan Park, Jaehyeon Jeong, Yongjun Kim, Jaeho Lee, Namhoon Lee

  ICLR 2025

  OptimizationEfficiency

• FedFwd: Federated Learning without Backpropagation

  Seonghwan Park, Dahun Shin, Jinseok Chung, Namhoon Lee

  ICML 2023 Workshop

  OptimizationEfficiency

• On the Effectiveness of Sharpness-Aware Minimization with Large Mini-batches

  Jinseok Chung, Seonghwan Park, Jaeho Lee, Namhoon Lee

  ICML 2023 Workshop

  Optimization

No publications match this filter.