TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition

• URL: http://arxiv.org/abs/2512.01248v1
• Date: Mon, 01 Dec 2025 03:49:00 GMT
• Title: TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
• Authors: Junyuan Zhang, Bin Wang, Qintong Zhang, Fan Wu, Zichen Wen, Jialin Lu, Junjie Shan, Ziqi Zhao, Shuya Yang, Ziling Wang, Ziyang Miao, Huaping Zhong, Yuhang Zang, Xiaoyi Dong, Ka-Ho Chow, Conghui He,
• Abstract summary: Table recognition (TR) aims to transform table images into semi-structured representations such as HTML or markdown.<n>We introduce TRivia, a self-supervised fine-tuning method that enables pretrained vision-language models to learn TR directly from unlabeled table images.<n>We present TRivia-3B, an open-sourced, compact, and state-of-the-art TR model that surpasses existing systems.
• Score: 54.85932472676512
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Table recognition (TR) aims to transform table images into semi-structured representations such as HTML or Markdown. As a core component of document parsing, TR has long relied on supervised learning, with recent efforts dominated by fine-tuning vision-language models (VLMs) using labeled data. While VLMs have brought TR to the next level, pushing performance further demands large-scale labeled data that is costly to obtain. Consequently, although proprietary models have continuously pushed the performance boundary, open-source models, often trained with limited resources and, in practice, the only viable option for many due to privacy regulations, still lag far behind. To bridge this gap, we introduce TRivia, a self-supervised fine-tuning method that enables pretrained VLMs to learn TR directly from unlabeled table images in the wild. Built upon Group Relative Policy Optimization, TRivia automatically identifies unlabeled samples that most effectively facilitate learning and eliminates the need for human annotations through a question-answering-based reward mechanism. An attention-guided module generates diverse questions for each table image, and the ability to interpret the recognition results and answer them correctly provides feedback to optimize the TR model. This closed-loop process allows the TR model to autonomously learn to recognize, structure, and reason over tables without labeled data. Leveraging this pipeline, we present TRivia-3B, an open-sourced, compact, and state-of-the-art TR model that surpasses existing systems (e.g., Gemini 2.5 Pro, MinerU2.5) on three popular benchmarks. Model and code are released at: https://github.com/opendatalab/TRivia

Related papers

• Can LLM Annotations Replace User Clicks for Learning to Rank? [112.2254432364736]
  Large-scale supervised data is essential for training modern ranking models, but obtaining high-quality human annotations is costly.<n>Click data has been widely used as a low-cost alternative, and with recent advances in large language models (LLMs), LLM-based relevance annotation has emerged as another promising annotation.<n> Experiments on both a public dataset, TianGong-ST, and an industrial dataset, Baidu-Click, show that click-supervised models perform better on high-frequency queries.<n>We explore two training strategies -- data scheduling and frequency-aware multi-objective learning -- that integrate both supervision signals.
  arXiv  Detail & Related papers  (2025-11-10T02:26:14Z)
• TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding [52.59372043981724]
  TableDART is a training-efficient framework that integrates multimodal views by reusing pretrained single-modality models.<n>In addition, we propose a novel agent to cross-modal knowledge integration by analyzing outputs from text- and image-based models.
  arXiv  Detail & Related papers  (2025-09-18T07:00:13Z)
• Multimodal Table Understanding [26.652797853893233]
  How to directly understand tables using intuitive visual information is a crucial and urgent challenge for developing more practical applications. We propose a new problem, multimodal table understanding, where the model needs to generate correct responses to various table-related requests. We develop Table-LLaVA, a generalist multimodal large language model (MLLM), which significantly outperforms recent open-source MLLM baselines on 23 benchmarks.
  arXiv  Detail & Related papers  (2024-06-12T11:27:03Z)
• UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining [22.031699293366486]
  We present UniTable, a training framework that unifies the training paradigm and training objective of table recognition. Our framework unifies the training objectives of all three TR tasks into a unified task-agnostic training objective: language modeling. UniTable's table parsing capability has surpassed both existing TR methods and general large vision-language models.
  arXiv  Detail & Related papers  (2024-03-07T15:44:50Z)
• Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval [92.13664084464514]
  The task of composed image retrieval (CIR) aims to retrieve images based on the query image and the text describing the users' intent. Existing methods have made great progress with the advanced large vision-language (VL) model in CIR task, however, they generally suffer from two main issues: lack of labeled triplets for model training and difficulty of deployment on resource-restricted environments. We propose Image2Sentence based Asymmetric zero-shot composed image retrieval (ISA), which takes advantage of the VL model and only relies on unlabeled images for composition learning.
  arXiv  Detail & Related papers  (2024-03-03T07:58:03Z)
• FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction [49.510163437116645]
  Click-through rate (CTR) prediction plays as a core function module in personalized online services. Traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality. Pretrained Language Models(PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality. We propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models(FLIP) for CTR prediction.
  arXiv  Detail & Related papers  (2023-10-30T11:25:03Z)
• Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition [55.362258027878966]
  We present momentum pseudo-labeling (MPL) as a simple yet effective strategy for semi-supervised speech recognition. MPL consists of a pair of online and offline models that interact and learn from each other, inspired by the mean teacher method. The experimental results demonstrate that MPL effectively improves over the base model and is scalable to different semi-supervised scenarios.
  arXiv  Detail & Related papers  (2021-06-16T16:24:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.