UniWorld is a unified framework for visual understanding, generation, and editing, excelling in over 20 visual tasks.

MultimodalSafetensors

Video-LLaVA is an open-source multimodal model trained by fine-tuning a large language model on multimodal instruction-following data, capable of generating interleaved images and videos.

MultimodalTransformers

MoE-LLaVA is a large vision-language model based on the Mixture of Experts architecture, achieving efficient multimodal learning through sparse activation parameters

MultimodalTransformers

MoE-LLaVA is a large-scale vision-language model based on a mixture of experts architecture, achieving efficient multimodal learning through sparsely activated parameters.

MultimodalTransformers

LanguageBind is a pretrained model that achieves multimodal semantic alignment through language, capable of binding various modalities such as video, audio, depth, and thermal imaging with language to enable cross-modal understanding and retrieval.

MultimodalTransformers

LanguageBind is a language-centric multimodal pretraining method that uses language as the bond between different modalities to achieve multimodal semantic alignment.

MultimodalTransformers

LanguageBind is a language-centric multimodal pretraining method that achieves semantic alignment by using language as the bridge between different modalities.

MultimodalTransformers

LanguageBind is a language-centric multimodal pretraining method that uses language as the bond between different modalities to achieve semantic alignment across video, infrared, depth, audio, and other modalities.

MultimodalTransformers

LanguageBind is a multimodal model that extends video-language pretraining to N modalities through language-based semantic alignment, accepted by ICLR 2024.

MultimodalTransformers

Video-LLaVA is a multimodal model that unifies visual representations through pre-projection alignment learning, capable of handling visual reasoning tasks for both images and videos.

MultimodalTransformers

LanguageBind is a language-centric multimodal pretraining method that uses language as the bond between different modalities to achieve semantic alignment.

MultimodalTransformers

LanguageBind is a language-centric multimodal pretraining method that uses language as the bond between different modalities to achieve semantic alignment across video, infrared, depth, audio, and other modalities.

MultimodalTransformers

LanguageBind is a multimodal pretraining framework that extends video-language pretraining to N modalities through language semantic alignment, accepted by ICLR 2024.

MultimodalTransformers

LanguageBind is a language-centric multimodal pre-training method that extends video-language pre-training to N modalities through language semantic alignment, achieving high-performance multimodal understanding and alignment.

MultimodalTransformers

LanguageBind is a pretraining framework that achieves multimodal semantic alignment through language as the bond, supporting joint learning of various modalities such as video, infrared, depth, and audio with language.

MultimodalTransformers