Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation Paper • 2511.22690 • Published Mar 31 • 1
Resolving the Identity Crisis in Text-to-Image Generation Paper • 2510.01399 • Published Oct 1, 2025 • 1
MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing Paper • 2507.13401 • Published Jul 16, 2025
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans Paper • 2506.20879 • Published Jun 25, 2025 • 1
Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models Paper • 2506.04244 • Published May 29, 2025 • 1
SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization Paper • 2502.19673 • Published Feb 27, 2025
Simple and Efficient Architectures for Semantic Segmentation Paper • 2206.08236 • Published Jun 16, 2022
4D Panoptic Segmentation as Invariant and Equivariant Field Prediction Paper • 2303.15651 • Published Mar 28, 2023
Resolving the Identity Crisis in Text-to-Image Generation Paper • 2510.01399 • Published Oct 1, 2025 • 1
Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation Paper • 2511.22690 • Published Mar 31 • 1
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans Paper • 2506.20879 • Published Jun 25, 2025 • 1