-
PositionIC: Unified Position and Identity Consistency for Image Customization
Paper • 2507.13861 • Published • 1 -
Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Paper • 2509.21278 • Published • 16 -
LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer
Paper • 2508.00477 • Published • 10 -
IC-Custom: Diverse Image Customization via In-Context Learning
Paper • 2507.01926 • Published • 1
Eungbean Lee
Eungbean
·
AI & ML interests
Computer Vision
Recent Activity
upvoted
a
paper
about 16 hours ago
OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer
upvoted
a
paper
about 16 hours ago
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
upvoted
a
paper
about 16 hours ago
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
Organizations
-
PositionIC: Unified Position and Identity Consistency for Image Customization
Paper • 2507.13861 • Published • 1 -
Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Paper • 2509.21278 • Published • 16 -
LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer
Paper • 2508.00477 • Published • 10 -
IC-Custom: Diverse Image Customization via In-Context Learning
Paper • 2507.01926 • Published • 1
models
0
None public yet
datasets
0
None public yet