Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

Hugging Face Daily Papers Papers
self-supervised-learning cross-representation co-evolution chart-understanding table-understanding code-understanding consistency-learning

Summary

This paper introduces CoCoEvolve, a self-supervised method that improves cross-representation understanding across charts, tables, and code by enforcing one-to-one consistency between representations, with training-time and test-time co-evolution objectives.

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/.
Original Article
View Cached Full Text

Cached at: 08/06/26, 05:49 AM

Paper page - Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

Source: https://huggingface.co/papers/2608.04926

Abstract

Aschartimages,tabulardata,andvisualizationcodeplayincreasinglyimportantrolesacrossdiversedomains,cross-representationunderstandingacrossthesemodalitiesposesfundamentalchallengesforAIsystems:therelationshipsacrossrepresentationsareinherentlyone-to-many,supervisionisambiguousandcostly,andmodeloptimizationlacksaprincipledsignalthatisbothdirection-adaptiveandrepresentation-generalizablebeyondtask-specificobjectives.WeintroduceCoCoEvolvetoimproveconsistencyacrosschart,table,andcoderepresentations.Insteadoftreatingcross-representationmappingasaone-to-manyproblem,wedefineexplicitone-to-onecorrespondencesandoptimizemodelsusingagreementbetweenrepresentations,withoutadditionalannotations.Duringtraining,CoCoEvolve@Trainperformsco-evolutionacrossthechart-table-codecycle,whileCoCoEvolve@Testappliesthesameconsistencyobjectiveatinferencetimefortest-timeco-optimization.WealsopresentCoCoEvolve@Eval,anevaluationsuitecoveringallsixcross-representationtasks.Acrossfourbenchmarks,CoCoEvolveimprovesperformanceinbothtraining-timeandtest-timesettings.Ourprojectpage:https://xhguo7.github.io/CoCoEvolve/.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.04926

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.04926 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.04926 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.04926 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution

arXiv cs.CL

CoEvolve proposes an agent-data mutual evolution framework for training LLM agents through closed-loop, interaction-driven learning that adapts both the agent and its training data distribution. The method extracts feedback signals from rollout trajectories to guide LLM-based task synthesis, demonstrating significant improvements (15-19% absolute gains) across multiple Qwen models on AppWorld and BFCL benchmarks.

Self-Evolving Deep Research via Joint Generation and Evaluation

arXiv cs.CL

Researchers from HKUST, ByteDance, and UCL propose SCORE, a co-evolutionary training framework that jointly trains an LLM as both a deep research report generator and an evaluator, using a meta-harness to dynamically adjust evaluation difficulty and prevent reward saturation. Experiments show consistent improvement in open-ended research report quality.

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations

arXiv cs.CL

This paper introduces CroCo, a method for cross-lingual contrastive preference tuning on self-generated responses, showing that a reward model trained on English preferences can effectively rank responses in other languages, improving model performance across 14 languages without language-specific annotations.