In the past year, MultiModal Large Language Models (MM-LLMs) have undergone
substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs …

With the widespread application of the Transformer architecture in various modalities,
including vision, the technology of large language models is evolving from a single modality …

In this report, we introduce the Gemini 1.5 family of models, representing the next generation
of highly compute-efficient multimodal models capable of recalling and reasoning over fine …

In this paper, we introduce InternVL 1.5, an open-source multimodal large language model
(MLLM) to bridge the capability gap between open-source and proprietary commercial …

Large language models (LLMs) have achieved remarkable progress in solving various
natural language processing tasks due to emergent reasoning abilities. However, LLMs …

We introduce MMMU: a new benchmark designed to evaluate multimodal models on
massive multi-discipline tasks demanding college-level subject knowledge and deliberate …

In this work, we discuss building performant Multimodal Large Language Models (MLLMs).
In particular, we study the importance of various architecture components and data choices …

We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed
by consolidating our insights into data, models, and visual representations in the LLaVA …

We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-
world vision and language understanding applications. Our approach is structured around …

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-
centric approach. While stronger language models can enhance multimodal capabilities, the …