Multimodal alignment

Deep Pre-Alignment for VLMs
Modular visual-encoder replacement for deeper multimodal pre-alignment.
Tianyu Yu, Kechen Fang, Zihao Wan, Kaidong Zhang, Yicheng Zhang, Jun Song, Bo Zheng, Yuan Yao ICML 2026
Paper Code
RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
Open-source AI feedback for trustworthy MLLM alignment.
Tianyu Yu, Haoye Zhang, Qiming Li, Qixin Xu, Yuan Yao, Da Chen, +8 more authors, Tat-Seng Chua, Maosong Sun CVPR 2025 Highlight
Paper Code