One Aligned LLM to Serve Them All: A Transfer Recipe for Training VLMs without Visual-Language Re-Alignment Jiazuo Yu Yunzhi Zhuge Lu Zhang Zi Huang Wei Zhou Dong Wang Huchuan Lu You He Long Chen Jul 2026 · International Journal of Computer Vision · Vol 134 · 0 citations · 57 references Computer Science DOI Semantic Scholar Save View source Cite { copied='apa'; setTimeout(() => { copied=null; open=false }, 1000) })" class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800"> Copy APA Copied ✓ { copied='mla'; setTimeout(() => { copied=null; open=false }, 1000) })" class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800"> Copy MLA Copied ✓ { copied='bibtex'; setTimeout(() => { copied=null; open=false }, 1000) })" class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800"> Copy BibTeX Copied ✓ Share