paper-with-me

Papers

TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding

2025-06-26 · Junwen Zhang, Pu Chen, Yin Zhang

Multimodal understanding of tables in real-world contexts is challenging due to the complexity of structure, symbolic density, and visual degradation (blur, skew, watermarking, incomplete structures or fonts, multi-span or hierarchically nested layouts). Existing multimodal large language models (MLLMs) struggle with such WildStruct conditions, resulting in limited performance and poor generalization. To address these challenges, we propose TableMoE, a neuro-symbolic Mixture-of-Connector-Experts (MoCE) architecture specifically designed for robust, structured reasoning over multimodal table data. TableMoE features an innovative Neuro-Symbolic Routing mechanism, which predicts latent semantic token roles (e.g., header, data cell, axis, formula) and dynamically routes table elements to specialized experts (Table-to-HTML, Table-to-JSON, Table-to-Code) using a confidence-aware gating strategy informed by symbolic reasoning graphs. To facilitate effective alignment-driven pretraining, we introduce the large-scale TableMoE-Align dataset, consisting of 1.2M table-HTML-JSON-code quadruples across finance, science, biomedicine and industry, utilized exclusively for model pretraining. For evaluation, we curate and release four challenging WildStruct benchmarks: WMMFinQA, WMMTatQA, WMMTabDialog, and WMMFinanceMath, designed specifically to stress-test models under real-world multimodal degradation and structural complexity. Experimental results demonstrate that TableMoE significantly surpasses existing state-of-the-art models. Extensive ablation studies validate each core component, emphasizing the critical role of Neuro-Symbolic Routing and structured expert alignment. Through qualitative analyses, we further showcase TableMoE's interpretability and enhanced robustness, underscoring the effectiveness of integrating neuro-symbolic reasoning for multimodal table understanding.

📄 PDF Abstract BibTeX arXiv:2506.21393

Code (1)

ai-agi/tablemoe 공식 구현

Similar Papers 제목 키워드 기반

StableMoE: Stable Routing Strategy for Mixture of Experts

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation i…

Language ModelingLanguage ModellingMachine TranslationMixture-of-Experts

StableMoE: Stable Routing Strategy for Mixture of Experts

2022-04-18 · ACL 2022 5 · Damai Dai, Li Dong, Shuming Ma, Bo Zheng 외

The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation i…

Language ModelingLanguage ModellingMachine TranslationMixture-of-Experts

TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts

2026-06-03 · Jiangyang He, Shaolin Zhu, Deyi Xiong arxiv

Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the large static parameter footprint of experts. Existing compression appr…

Code Generation

Agentic Neuro-Symbolic Planning and Commissioning for Human-in-the-Loop Industrial Robotics with Digital Twins

2026-06-06 · Zhihao Liu, Victor Nan Fernandez-Ayala, Tianyu Wang, Qiang Qin 외 arxiv

Flexible robotic automation requires systems that interpret operator intent, verify physical feasibility, and recover from execution failures across both the planning and execution stages. This paper proposes an agentic …

CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding

2022-12-21 · Yijiang River Dong, Lara J. Martin, Chris Callison-Burch

Story generation and understanding -- as with all NLG/NLU tasks -- has seen a surge in neurosymbolic work. Researchers have recognized that, while large language models (LLMs) have tremendous utility, they can be augment…

Story GenerationTask 2