🧑🔬 Jinhe Bi — papers of 2025 — 1 paper, the most cited first1 paper · all years of Jinhe BiLLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Jinhe Bi, Yujun Wang, Haokun Chen, et al.2025 · 24 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/jinhe-bi/year/2025/