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 …

Large models represent a groundbreaking advancement in multiple application fields,
enabling remarkable achievements across various tasks. However, their unprecedented …

In this report, we present the latest model of the Gemini family, Gemini 1.5 Pro, a highly
compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Although Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit
impressive skills in various domains, their ability for mathematical reasoning within visual …

Large Language Models (LLMs) have drawn a lot of attention due to their strong
performance on a wide range of natural language tasks, since the release of ChatGPT in …

Recent efforts have incorporated large language models (LLMs) with external resources (eg,
the Internet) or internal control flows (eg, prompt chaining) for tasks requiring grounding or …

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 …

In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-
modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating …

This study highlights the potential of fine-tuned ChatGPT (GPT-3.5) for automatically scoring
student written constructed responses using example assessment tasks in science …