GithubHelp home page GithubHelp logo

x-plug / mplug-halowl Goto Github PK

View Code? Open in Web Editor NEW
72.0 1.0 2.0 14.28 MB

mPLUG-HalOwl: Multimodal Hallucination Evaluation and Mitigating

License: MIT License

Python 92.48% HTML 1.36% JavaScript 1.78% CSS 0.32% Shell 4.05%
mllm multimodal-large-language-models benchmark contrastive-learning hallucinations multimodal-hallucination

mplug-halowl's People

Contributors

chaoyajiang avatar junyangwang0410 avatar xhyandwyy avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

siliciuss rbsohee

mplug-halowl's Issues

Dataset release

Great work! Will you release the hallucination caption dataset used in HACL? Thanks.

Specific version of LLaVA used

Your work is really fascinating! Could you please provide the specific version of LLaVA (not 1.5) used in main experiments? Thank you!

How to draw the figures in hacl?

1720146270994
We have recently been exploring methods to reduce the modality gap in multimodal large models, but have been struggling to determine the most effective way to validate the efficacy of our approaches. Fortunately, we came across your excellent paper, HACL, and were particularly inspired by the image mentioned above. We are reaching out to inquire about how to create such a visual representation.
Looking forward to your reply!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.