Publications

In this report, we introduce the Gemini 2.X model family. Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash …

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this …

Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. However, generalist LMMs often suffer from …

Recent empirical evidence indicates that transformer based in-context learning performs better when using a prefix language model …

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the …

We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control to …

Most Outside-Knowledge Visual Question Answering (OK-VQA) systems employ a two-stage framework that first retrieves external knowledge …

The problem of knowledge-based visual question answering involves answering questions that require external knowledge in addition to …

Most recent state-of-the-art Visual Question Answering (VQA) systems are opaque black boxes that are only trained to fit the answer …

Daily scenes are complex in the real world due to occlusion, undesired lighting conditions, etc. Although humans handle those …

Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because …

Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We …

We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from …