See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
Paper
• 2602.20951 • Published
• 12
Jonghyun Lee
Jhyun17
AI & ML interests
On-device AI, Responsible AI, Time-series forecasting
Recent Activity
authored
a paper
about 24 hours ago
Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation authored
a paper
about 24 hours ago
Removing Undesirable Feature Contributions Using Out-of-Distribution
Data authored
a paper
about 24 hours ago
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on
Diverse Video Games Organizations
None yet
upvoted a paper 1 day ago