VCR: Visual Caption RestorationJan 1, 2024·Tianyu Zhang*,Suyuchen Wang*,Lu Li,Ge Zhang,Perouz Taslakian,Sai Rajeswar,Jie Fu,Bang Liu,Yoshua Bengio· 0 min read Cite DOI URLTypeJournal articlePublicationCoRRLast updated on Nov 10, 2024 ← Resonance RoPE: Improving Context Length Generalization of Large Language Models Jan 1, 2024DiffTune: A Diffusion-Based Approach to Diverse Instruction-Tuning Data Generation Jan 1, 2023 →