HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 9 天前AI 评分34
SciGen-Verifier：面向科学图像生成可解释验证的多模态推理器
AI 导读
SciGen-Verifier 是一个用于科学图像生成可解释验证的多模态推理器，通过冷启动监督微调加课程式两阶段强化学习训练，在自建基准 SciGen-Verify 上性能可媲美更大的闭源模型。该基准覆盖指令遵循、多学科推理与世界知识，采用二值判断、解释与纠错编辑指令的三层协议。它还可作为在线 critic 用于图像的迭代修正。
正文
Abstract:In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and a teacher must grade the drawing as carefully as the text. Recent advances in unified multimodal models have enabled scientific image generation, yet verifying the correctness of these specialized visual outputs remains a critical bottleneck: errors often arise from intricate domain knowledge, structural reasoning, and multi-step instruction rather than surface-level artifacts. Existing verifiers mainly target natural images and compress judgement into scalar scores, leaving scientific coverage and explainable feedback for error correction underexplored. To bridge this gap, we make three main contributions. (1) We construct SciGen-Verify, a benchmark dedicated to explainable verification of scientific image generation, spanning instruction following, multidisciplinary reasoning, and world knowledge domains. It contains a three-tier hierarchical protocol over the binary judgement, supporting explanation, and corrective editing instruction. (2) We develop SciGen-Verifier, a reasoning-driven multimodal verifier trained via cold-start supervised fine-tuning followed by a curriculum-based two-stage reinforcement learning pipeline. The rubric-guided process rewards first strengthen scientific reasoning exploration and outcome rewards subsequently align output with ground-truth annotation. (3) On SciGen-Verify, SciGen-Verifier achieves competitive performance against much larger proprietary models. It further serves as a practical online critic for iterative image rectification.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2609.33399 [cs.CV] |
| (or arXiv:2609.33399v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2609.33399 arXiv-issued DOI via DataCite |
Submission history
From: Jiali Chen [view email]
[v1]
Sun, 27 Sep 2026 09:23:36 UTC (7,197 KB)
[v2]
Tue, 29 Sep 2026 03:03:04 UTC (7,197 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org