open-compass / open-compass/VLMEvalKit

Adding LiveXiv - a live benchmark

Open
#976 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi,
Thanks for the super important work of standardize evaluation!
I want to add my recent ICLR 2025 benchmark LiveXiv Which is a live and updated benchmark.
Is there a support for live benchmark or I need to add each version each time?

Thanks,
Nimrod

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

The issue names the LiveXiv dataset on Hugging Face but no repository files, tests, or entry points. Start by locating how VLMEvalKit registers benchmark datasets and handles versioned data, then determine whether a live benchmark can be supported without adding each version separately. Done means the supported workflow is clearly defined and LiveXiv integration is covered by the relevant validation or evaluation checks.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning, testing-qa
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.