Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
Xuehang Guo, Pengyuan Li, Tom Hope, Tirthankar Ghosal, Manling Li, Qingyun Wang
cs.LG, cs.AI, cs.CL
Submitted: 2026-08-05
Project page: https://xhguo7.github.io/CoCoEvolve
License: http://creativecommons.org/licenses/by/4.0/
The gist: As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding across these modalities poses fundamental challenges
Terminology
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/.
Sources
- Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages
- The Llama 3 Herd of Models
- UniXcoder: Unified Cross-Modal Pre-training for Code Representation
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- Anagent For Enhancing Scientific Table & Figure Analysis
- From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
- DINOv2: Learning Robust Visual Features without Supervision
- Learning Transferable Visual Models From Natural Language Supervision
- CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models
- Large Language Models are Inconsistent and Biased Evaluators
- From Charts to Code: A Hierarchical Benchmark for Multimodal Models
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Qwen3 Technical Report
- ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Group Sequence Policy Optimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks