LLaVA-v-1.5

LLaVA-v-1.5 is a dataset/benchmark used to evaluate the performance of Multimodal Large Language Models (MLLMs) on vision-language tasks.

Papers using LLaVA-v-1.5 (3)

SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation2025 · 17 cites$\mathcal{V}isi\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs2025Sineproject: Machine Unlearning For Stable Vision Language Alignment2025