←Story detail

Trending story

Multiple papers from the Jiangsu Provincial Key Laboratory of Language Computing and Applications have been accepted by ACM MM 2026.

1 reports1 story updatesUpdated Oct 27 12:59

Understand this story

AI overview

The CharTool achievement from the Jiangsu Provincial Key Laboratory of Language Computing and Applications has been selected for ACM MM 2026. According to a report by Jiwei.com on October 27, 2026, this achievement enhances multimodal chart reasoning through two types of tools: image cropping and code computation. CharTool-7B improves by 8.0 percentage points over the base model on the CharXiv reasoning task and by 9.78 percentage points on ChartQAPro, with its average score across six benchmarks surpassing proprietary models such as GPT-4o. The report states that the related capabilities will strengthen AISpeech's DFM and 1+N distributed agent system for chart interpretation in smart office and scenarios such as finance and government affairs. There are currently no further developments.

AI-generated from public reports

Latest development · Report

Research from the Jiangsu Provincial Key Laboratory of Language Computing and Applications Selected for ACM MM 2026: Enhancing Multimodal Large Model Capabilities with Tool-Augmented Reasoning

Developments

1 confirmed developments

  1. Multiple Papers from Jiangsu Provincial Key Laboratory of Language Computing and Applications Accepted by ACM MM 2026

    Source:Jiwei.com

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 27

  1. Jiwei.com

    Research from the Jiangsu Provincial Key Laboratory of Language Computing and Applications Selected for ACM MM 2026: Enhancing Multimodal Large Model Capabilities with Tool-Augmented Reasoning

    The CharTool research from the Jiangsu Provincial Key Laboratory of Language Computing and Applications has been accepted to ACM MM 2026, enhancing multimodal chart reasoning through two types of tools: image cropping and code computation. CharTool-7B improves over its base model by 8.0 percentage points on the CharXiv reasoning task and by 9.78 percentage points on ChartQAPro, with its average score across six benchmarks surpassing proprietary models such as GPT-4o. The related capabilities will strengthen AISpeech's DFM and 1+N distributed agent system for chart interpretation in scenarios such as smart office, finance, and government affairs.

Related stories

  1. Related storiesOpenAI launches GPT-6.1 Terra on ChatGPT Work and Codex
  2. Related storiesNvidia releases Nemotron 3.5 Super VL and Bolt models
  3. Related storiesEnglish translation is being prepared.
  4. Related storiesEnglish translation is being prepared.