VIEScore2, a unified evaluator for image generation and editing tasks with optional conditioning images, outperforms both general-purpose VLMs and specialized spatial evaluators on three of six benchmarks in per-image grid IoU and ranks among the top three on five, including datasets beyond its training sources.
Abstract
Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce VIEScore2, a unified evaluator for image generation and editing tasks with optional conditioning images. VIEScore2 represents an image as an N x N grid and jointly predicts quality scores and defect locations in a single model pass. Its text-native grid representation provides a common interface for heterogeneous spatial supervision and enables directly verifiable post-training objectives. We train on 38K examples spanning score-only, localization-only, and joint supervision across generation and editing tasks. Starting from supervised fine-tuning, we further apply GRPO to improve defect localization using rewards that combine cell-level Dice overlap, score accuracy, and output-format validity. A parameter-free parser converts the structured predictions into readable explanations. On the primary suite, VIEScore2 achieves an overall-score SRCC of 0.601, compared with 0.491 for Gemini-3-Flash, the strongest zero-shot general-purpose VLM baseline under matched inputs. For defect localization, VIEScore2 outperforms both general-purpose VLMs and specialized spatial evaluators on three of six benchmarks in per-image grid IoU and ranks among the top three on five, including datasets beyond its training sources.
VisExMEM is introduced, a reference-free evaluator that decomposes captions into atomic claims, localizes visual evidence, verifies each claim, and averages claim-level support into a global score, which achieves the highest descriptive composite among open-source evaluators in a comparison.
Subhadeep Roy, Christoph Leiter, Steffen Eger· 0 citations
Unified multimodal models combine image understanding and generation within one system, creating an opportunity to improve both capabilities through paired image--text supervision. We examine the outputs of a pretrained unified model in both directions and observe a loss of specificity: generated images can contain the...
Hao-Yue Bai, Yin-Yi Luo, Yi-Cheng He et al.· 0 citations
We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications, the model processes text, reference images...
Can-Miao Fu, Chen Li, Guo-Hui Zhang et al.· 0 citations
Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas. Existing work covers only subsets of these capabilities and lacks large-scale slide-native supervision and diagnostic evaluatio...
Jia-Hao Wang, Xi-Yan Jiang, Chen-Yuan Wu et al.· 0 citations
We present an inference-time approach that enhances the visual diversity of image sets generated by text-to-image models, without compromising the average image quality. Our method leverages the intrinsic geometry of hidden representations in pretrained models to diversify images generated from the same prompt. First,...
Qing-Tao Yu, Zhen Wang, N. Lai et al.· 0 citations
To support the experience-acquisition component of recursive self-improvement (RSI), WeGenEvoStudio is developed, a unified multi-agent harness for RSI-oriented learning that integrates model-conditioned failure diagnosis, retrieval-grounded data construction, supervised adaptation, and re-evaluation.
Jun He, Can-Miao Fu, Ying Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.