Seohyun Lee
Scholar

Seohyun Lee

Google Scholar ID: WXTvNO8AAAAJ
Korea University
VLMVLAGenerative Models
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
0
 
H-index
0
 
i10-index
0
 
Publications
1
 
Co-authors
0
 
Contact
Emailhappy8825@korea.ac.krGitHubOpen ↗LinkedInOpen ↗
Publications
8 items
Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs
2026
Cited
0
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
2026
Cited
0
Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme
2026
Cited
0
Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback
2026
Cited
0
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
2026
Cited
0
TAP: Two-Stage Adaptive Personalization of Multi-task and Multi-Modal Foundation Models in Federated Learning
2025
Cited
0
Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning
2025
Cited
0
ODPG: Outfitting Diffusion with Pose Guided Condition
2025
Cited
0
Resume (English only)
Education
  • Undergraduate student at Korea University
Background
  • Primary focus on Computer Vision, with a particular interest in Vision-Language Models (VLM) and Generative Models.
Co-authors
0 total
Co-authors: 0 (list not available)