LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Xun Xiao (ORCID: https://orcid.org/0000-0002-9810-2448)
- Artur Hecker (ORCID: https://orcid.org/0000-0003-3604-2686)
- Haokun Chen
- Yunpu Ma (ORCID: https://orcid.org/0000-0001-6112-8794)
- Volker Tresp (ORCID: https://orcid.org/0000-0001-9428-3686)
- Yujun Wang (ORCID: https://orcid.org/0000-0002-0921-0122)
- Jinhe Bi
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.739
- Citations
- 4
- Primary Topic
- Gaze Tracking and Assistive Technology
- Type
- article
- Field-Weighted Citation Impact
- 7.74
Funders
- Friedrich-Alexander-Universität Erlangen-Nürnberg
- Deutsche Forschungsgemeinschaft