Zhuming Lian — accepted AI-conference papers

2026

Does FLUX Already Know How to Perform Physically Plausible Image Composition?

Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang, Chen Zhao, Adams Wai-Kin Kong

ICLR 2026poster

Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections) and diverse, high-resolution inputs. Modern text-to-image diffusion models (e.g., SD3.5, FLUX) already encode essential…

Cited by 0 Source ↗code ↗Scholar ↗

2026

DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag Editing

Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu +1

ICLR 2026poster

Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With the shift from UNet-based DDPMs to more scalable DiT with fl…

Cited by 0 Source ↗code ↗Scholar ↗