open-compass / open-compass/VLMEvalKit

Proposal to Add “Document Understanding” Section to the Open VLM Leaderboard

Open
#769 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.4k
Forks
768
Avg merge
1d 10h
Merged PRs (30d)
17

Description

Propose the addition of a “Document Understanding” section to the Open VLM Leaderboard. This new section would focus on evaluating models’ capabilities in comprehending and processing document-based information, which is a critical aspect of vision-language integration for enterprise use cases.

Proposed Benchmark Datasets to be included in Document Understanding:

  • DocVQA
  • ChartVQA
  • TextVQA
  • InfoVQA
  • LiveXivVQA
  • LiveXivTQA

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing how the Open VLM Leaderboard currently organizes evaluation sections and registers benchmark datasets. Define the scope for a new Document Understanding section covering DocVQA, ChartVQA, TextVQA, InfoVQA, LiveXivVQA, and LiveXivTQA. Done means the section and its dataset coverage are implemented, but this issue does not identify the relevant files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.