YoungjunLee's picture

3 3

YoungjunLee

e0jun

·

e0jun

AI & ML interests

continual learning

Recent Activity

upvoted a paper 1 day ago

Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

liked a dataset 4 days ago

KRAFTON/ArtiBench

upvoted a paper 4 days ago

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

Paper • 2602.21760 • Published 3 days ago • 12

upvoted a paper 4 days ago

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis

Paper • 2602.20951 • Published 4 days ago • 13

upvoted a collection 6 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 519