Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences

v1v2 (latest)

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences

2 June 2025

ArXiv (abs)PDF HTML

Papers citing "Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences"

7 / 7 papers shown

Title
HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models Sushant Gautam Michael A. Riegler Pål Halvorsen VLM 158 0 0 16 Nov 2025
Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions Eyal Gutflaish Eliran Kachlon Hezi Zisman Tal Hacham Nimrod Sarid ... Saar Huberman Gal Davidi Guy Bukchin Kfir Goldberg Ron Mokady DiffM VLM 213 1 0 10 Nov 2025
PreferThinker: Reasoning-based Personalized Image Preference Assessment Shengqi Xu Xinpeng Zhou Y. Zhang Ming-Yu Liu Tao Liang Tianyu Zhang Yalong Bai Zuxuan Wu W. Zuo 177 0 0 01 Nov 2025
RealDPO: Real or Not Real, that is the Preference Guo Cheng Danni Yang Ziqi Huang Jianlou Si Chenyang Si Ziwei Liu VGen 286 0 0 16 Oct 2025
Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication M. Behmanesh Erkan Turan M. Ovsjanikov 124 0 0 11 Sep 2025
Unified Multimodal Model as Auto-Encoder Zhiyuan Yan Kaiqing Lin Zongjian Li Junyan Ye Hui Han ... Xue Xu Xinyan Xiao Jingdong Wang Haifeng Wang Li Yuan 298 1 0 11 Sep 2025
The Telephone Game: Evaluating Semantic Drift in Unified Models Sabbir Mollah Rohit Gupta S. Swetha Qingyang Liu Ahnaf Munir Mubarak Shah VLM 131 1 0 04 Sep 2025