返回精选
AI 精选动态 智能评分 67

SenseNova-U1-8B-MoT 信息图数学能力突破

来源: twitter关注列表
作者: ModelScope (@ModelScope2022)
发布于: 2026-06-30
收录于: 2026-06-30
AI 推荐理由
新增开源 SOTA 模型,基准与性能提升具体量化,对信息图 domain 的开发者有直接应用价值,建议点开原文获取详细技术参数和使用场景
核心解读
SenseNova Labs 开源了专为信息图任务设计的 SenseNova-U1-8B-MoT 模型,仅在 BizGenEval 和 IGenBench 基准上达成 SOTA 性能,提升了图表准确率、文本渲染、布局理解和 arXiv 样式页面质量,同时减少了意外的黑底,基于 SenseNova-U1 的统一多模态架构整合了视觉理解、推理和生成能力。
全文
Meet SenseNova-U1-8B-MoT-Infographic-V2! This model is designed exactly for dense content, complex layouts, text-heavy visuals. 🤖 https://t.co/ytyUq5j2aH 🏆 Open-source SOTA performance Strong results on infographic benchmarks, including BizGenEval and IGenBench. 📊 Improves chart accuracy, text rendering, size appropriateness, layout understanding, and arXiv-style page quality, while reducing unintended black backgrounds. 🧠 Native unified multimodal architecture Built on SenseNova-U1, unifying visual understanding, reasoning, and generation in one model. ![photo](https://pbs.twimg.com/media/HMEtb2AXcAAzwum.jpg) ![photo](https://pbs.twimg.com/media/HMEtbzlWsAAYC24.jpg) ![photo](https://pbs.twimg.com/media/HMEtbz3XYAAhZRq.jpg) ![photo](https://pbs.twimg.com/media/HMEtbvUWsAAqfvK.jpg)
#大模型#开源#技术突破