# CoCoEvolve：一致性驱动的自监督跨表征协同进化

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-05 08:00
- AIHOT 分数：43
- AIHOT 链接：https://aihot.virxact.com/items/cmsgzgofm05nfroxztpl41c9j
- 原文链接：https://arxiv.org/abs/2608.04926

## AI 摘要

CoCoEvolve 通过定义显式一对一对应关系，以表征间一致性为优化目标，无需额外标注即可提升图表、表格与代码三种模态间的跨表征理解。训练时在图表-表格-代码循环中协同进化，推理时应用同一目标进行测试时协同优化，并配套覆盖全部六项跨表征任务的评测套件。在四个基准上，该方法在训练与测试时设置下均提升了性能。

## 正文

As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding across these modalities poses fundamental challenges for AI systems: the relationships across representations are inherently one-to-many, supervision is ambiguous and costly, and model optimization lacks a principled signal that is both direction-adaptive and representation-generalizable beyond task-specific objectives. We introduce CoCoEvolve to improve consistency across chart, table, and code representations. Instead of treating cross-representation mapping as a one-to-many problem, we define explicit one-to-one correspondences and optimize models using agreement between representations, without additional annotations. During training, CoCoEvolve@Train performs co-evolution across the chart-table-code cycle, while CoCoEvolve@Test applies the same consistency objective at inference time for test-time co-optimization. We also present CoCoEvolve@Eval, an evaluation suite covering all six cross-representation tasks. Across four benchmarks, CoCoEvolve improves performance in both training-time and test-time settings. Our project page: https://xhguo7.github.io/CoCoEvolve/.