arxiv:2609.31847
👋 Open to Work
Yanlin Li
yanlinli
AI & ML interests
Trustworthy Agentic AI, Unified Multimodal Models, Human-Centered AI
Recent Activity
upvoted a paper 2 days ago
EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment upvoted a paper 4 days ago
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models upvoted a paper 6 days ago
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?Organizations
models 0
None public yet
datasets 10
yanlinli/image-editing-evaluation-handoff
Updated • 176
yanlinli/video-editing-evaluation-65f
Viewer • Updated • 14 • 109
yanlinli/3d-editing-benchmark-results
Viewer • Updated • 604 • 92
yanlinli/video-editing-benchmark-results
Updated • 103
yanlinli/image-editing-benchmark-results
Viewer • Updated • 14.6k • 48
yanlinli/Nano3D_rendered_v2
Preview • Updated • 32
yanlinli/Nano3D_rendered
Viewer • Updated • 2k • 593
yanlinli/edited
Updated • 95
yanlinli/real
Viewer • Updated • 1.21k • 97
yanlinli/UniM
Updated • 92 • 4