新的AC-JEPA架构通过不完美数据改进视觉到符号的翻译

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了一种锚定跨模态联合嵌入预测架构（AC-JEPA），旨在改进视觉到符号的翻译，尤其是在配对数据稀缺或不完美的科学领域。该新模型集成了联合嵌入目标和因果监督微调（SFT），以预测跨模态的中间状态。在WildMol基准测试中使用光学化学结构识别进行测试时，AC-JEPA在不完美数据下达到了80.23%的准确率，显著优于直接SFT，后者准确率下降到63.47%。 AI

影响该架构可以增强AI解释和翻译复杂科学数据的能力，可能加速化学等领域的研究。

排序理由该集群描述了一篇详细介绍新型AI架构的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍新型AI架构的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Chaofei Hong, Ziyang Chen, Baochen Wang, Christina Yi Jin, Qing Zhang · 2026-10-28 04:00

AC-JEPA：用于视觉到符号翻译的锚定跨模态联合嵌入预测架构

arXiv:2610.36493v1 Announce Type: new Abstract: Cross-modal translation requires models to capture shared semantics across modalities while preserving the fine-grained structure required by the target modality. Yet in real-world scientific domains, paired data are often imperfect…

本文如何被排名

报道来源 [1]

AC-JEPA：用于视觉到符号翻译的锚定跨模态联合嵌入预测架构

相关实体

相关话题