Paper Detail
Xuehang Guo, Pengyuan Li, Tom Hope, Tirthankar Ghosal, Manling Li, Qingyun Wang
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/.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{guo2026consistency,
title = {Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning},
author = {Xuehang Guo and Pengyuan Li and Tom Hope and Tirthankar Ghosal and Manling Li and Qingyun Wang},
year = {2026},
abstract = {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 impr},
url = {https://huggingface.co/papers/2608.04926},
keywords = {huggingface daily},
eprint = {2608.04926},
archiveprefix = {arXiv},
}
{}