CoCoEvolve: Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning</p>\n","updatedAt":"2026-08-06T03:39:13.797Z","author":{"_id":"6787f14e48e947a8776dc8be","avatarUrl":"/avatars/835f28fd611c49db82971403232bac46.svg","fullname":"Xuehang Guo","name":"xuehang","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8184992074966431},"editors":["xuehang"],"editorAvatarUrls":["/avatars/835f28fd611c49db82971403232bac46.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.04926","authors":[{"_id":"6a7401adc5e410d076869b3d","user":{"_id":"6787f14e48e947a8776dc8be","avatarUrl":"/avatars/835f28fd611c49db82971403232bac46.svg","isPro":true,"fullname":"Xuehang Guo","user":"xuehang","type":"user","name":"xuehang"},"name":"Xuehang Guo","status":"claimed_verified","statusLastChangedAt":"2026-08-06T08:45:05.527Z","hidden":false},{"_id":"6a7401adc5e410d076869b3e","name":"Pengyuan Li","hidden":false},{"_id":"6a7401adc5e410d076869b3f","name":"Tom Hope","hidden":false},{"_id":"6a7401adc5e410d076869b40","name":"Tirthankar Ghosal","hidden":false},{"_id":"6a7401adc5e410d076869b41","name":"Manling Li","hidden":false},{"_id":"6a7401adc5e410d076869b42","name":"Qingyun Wang","hidden":false}],"publishedAt":"2026-08-05T00:00:00.000Z","submittedOnDailyAt":"2026-08-06T00:00:00.000Z","title":"Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning","submittedOnDailyBy":{"_id":"6787f14e48e947a8776dc8be","avatarUrl":"/avatars/835f28fd611c49db82971403232bac46.svg","isPro":true,"fullname":"Xuehang Guo","user":"xuehang","type":"user","name":"xuehang"},"summary":"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/.","upvotes":4,"discussionId":"6a7401aec5e410d076869b43"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6a6aa101b7f4852961dd6caf","avatarUrl":"/avatars/dcd9edd4361eff66d69911dea531334c.svg","isPro":false,"fullname":"Patricia Davis","user":"Orbit-TrailV","type":"user"},{"_id":"6a6aa38fbbca071c718a29de","avatarUrl":"/avatars/93253032d7014e832fa66c1575e1fb9e.svg","isPro":false,"fullname":"James Johnson","user":"Kestrel-Evan","type":"user"},{"_id":"6a6d5873e4c3f57705be2b86","avatarUrl":"/avatars/b922d6f1452645ef048cc81199860c07.svg","isPro":false,"fullname":"Steven Smith","user":"steven-smith","type":"user"},{"_id":"6a701c6c518039c9718c3b96","avatarUrl":"/avatars/2e6fa06a429776f305200495892836d6.svg","isPro":false,"fullname":"Daniel Martinez","user":"james-2606086","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.04926.md","query":{}}">
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
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 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/.
Community
CoCoEvolve: Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.04926 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.04926 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.04926 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.