default author photo

Xiangrui Chen

Hefei University of Technology

193 Tunxi Rd

Baohe

Hefei

China

SCHOLARLY PAPERS

3

DOWNLOADS

139

TOTAL CITATIONS

0

Scholarly Papers (3)

1.

Training-Free Position and Structure Controllable Multi-Object Image Editing

Number of pages: 13 Posted: 13 Oct 2025
affiliation not provided to SSRN, Hefei University of Technology, Hefei University of Technology, affiliation not provided to SSRN, Donghua University, Yunnan University and Harbin Institute of Technology
Downloads 66 (916,100)

Abstract:

Loading...

Diffusion model, Training-free, Multi-object editing, Energy-guided Latent optimization, Attention guidance

2.

Caption-Guided Contrastive Diffusion for Image Translation

Number of pages: 13 Posted: 15 Jul 2025
Qi Si, Zhao Zhang, Xiangrui Chen, Bo Wang, Mingbo Zhao and Yun Yang
affiliation not provided to SSRN, Hefei University of Technology, Hefei University of Technology, affiliation not provided to SSRN, Donghua University and Yunnan University
Downloads 43 (1,157,785)

Abstract:

Loading...

Diffusion model, Training-free, Image translation, Attention guidance.

3.

Writtenbench: Answer Sheets Benchmark For  Multimodal Large Language Models

Number of pages: 8 Posted: 07 Jul 2025
Hefei University of Technology, Hefei University of Technology, Hefei University of Technology, Hefei University of Technology, affiliation not provided to SSRN, Yunnan University and Hefei University of Technology
Downloads 30 (1,318,317)

Abstract:

Loading...

Multimodal Large Language Models (MLLMs), Optical Character Recognition (OCR), Answer Sheet Dataset, Dual-branch Reuse Mechanism