Gemma 3 Technical Report

We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision understanding abilities, a wider coverage of languages and longer context - at least 128K tokens. We also change the architecture of the model to reduce the KV-cache memory that tends to explode with long context. This is achieved by increasing the ratio of local to global attention layers, and keeping the span on local attention short. The Gemma 3 models are trained with distillation and achieve superior performance to Gemma 2 for both pre-trained and instruction finetuned versions. In particular, our novel post-training recipe significantly improves the math, chat, instruction-following and multilingual abilities, making Gemma3-4B-IT competitive with Gemma2-27B-IT and Gemma3-27B-IT comparable to Gemini-1.5-Pro across benchmarks. We release all our models to the community.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

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 over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. Gemini 1.5 Pro achieves near-perfect recall on long-context retrieval tasks across modalities, improves the state-of-the-art in long-document QA, long-video QA and long-context ASR, and matches or surpasses Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5 Pro's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 2.1 (200k) and GPT-4 Turbo (128k). Finally, we highlight surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

PaLI-X: On Scaling up a Multilingual Vision and 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 components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$

Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves. Scaling can be complicated due to various factors including the need to distribute computation on supercomputer clusters (e.g., TPUs), prevent bottlenecks when infeeding data, and ensure reproducible results. In this work, we present two software libraries that ease these issues: $\texttt{t5x}$ simplifies the process of building and training large language models at scale while maintaining ease of use, and $\texttt{seqio}$ provides a task-based API for simple creation of fast and reproducible training data and evaluation pipelines. These open-source libraries have been used to train models with hundreds of billions of parameters on datasets with multiple terabytes of training data. Along with the libraries, we release configurations and instructions for T5-like encoder-decoder models as well as GPT-like decoder-only architectures. $\texttt{t5x}$ and $\texttt{seqio}$ are open source and available at https://github.com/google-research/t5x and https://github.com/google/seqio, respectively.

Continental-Scale Building Detection from High Resolution Satellite Imagery

Identifying the locations and footprints of buildings is vital for many practical and scientific purposes. Such information can be particularly useful in developing regions where alternative data sources may be scarce. In this work, we describe a model training pipeline for detecting buildings across the entire continent of Africa, using 50 cm satellite imagery. Starting with the U-Net model, widely used in satellite image analysis, we study variations in architecture, loss functions, regularization, pre-training, self-training and post-processing that increase instance segmentation performance. Experiments were carried out using a dataset of 100k satellite images across Africa containing 1.75M manually labelled building instances, and further datasets for pre-training and self-training. We report novel methods for improving performance of building detection with this type of model, including the use of mixup (mAP +0.12) and self-training with soft KL loss (mAP +0.06). The resulting pipeline obtains good results even on a wide variety of challenging rural and urban contexts, and was used to create the Open Buildings dataset of 516M Africa-wide detected footprints.

Representation learning from videos in-the-wild: An object-centric approach

We propose a method to learn image representations from uncurated videos. We combine a supervised loss from off-the-shelf object detectors and self-supervised losses which naturally arise from the video-shot-frame-object hierarchy present in each video. We report competitive results on 19 transfer learning tasks of the Visual Task Adaptation Benchmark (VTAB), and on 8 out-of-distribution-generalization tasks, and discuss the benefits and shortcomings of the proposed approach. In particular, it improves over the baseline on all 18/19 few-shot learning tasks and 8/8 out-of-distribution generalization tasks. Finally, we perform several ablation studies and analyze the impact of the pretrained object detector on the performance across this suite of tasks.

Self-Supervised Learning of Video-Induced Visual Invariances

We propose a general framework for self-supervised learning of transferable visual representations based on video-induced visual invariances (VIVI). We consider the implicit hierarchy present in the videos and make use of (i) frame-level invariances (e.g. stability to color and contrast perturbations), (ii) shot/clip-level invariances (e.g. robustness to changes in object orientation and lighting conditions), and (iii) video-level invariances (semantic relationships of scenes across shots/clips), to define a holistic self-supervised loss. Training models using different variants of the proposed framework on videos from the YouTube-8M data set, we obtain state-of-the-art self-supervised transfer learning results on the 19 diverse downstream tasks of the Visual Task Adaptation Benchmark (VTAB), using only 1000 labels per task. We then show how to co-train our models jointly with labeled images, outperforming an ImageNet-pretrained ResNet-50 by 0.8 points with 10x fewer labeled images, as well as the previous best supervised model by 3.7 points using the full ImageNet data set.

High-Fidelity Image Generation With Fewer Labels

Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images at high resolution, they rely on a vast quantity of labeled data. In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform state-of-the-art (SOTA) on both unsupervised ImageNet synthesis, as well as in the conditional setting. In particular, the proposed approach is able to match the sample quality (as measured by FID) of the current state-of-the art conditional model BigGAN on ImageNet using only 10% of the labels and outperform it using 20% of the labels.

Self-Supervised Generative Adversarial Networks

Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labelled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, to close the gap between conditional and unconditional GANs. In particular, we allow the networks to collaborate on the task of representation learning, while being adversarial with respect to the classic GAN game. The role of self-supervision is to encourage the discriminator to learn meaningful feature representations which are not forgotten during training. We test empirically both the quality of the learned image representations, and the quality of the synthesized images. Under the same conditions, the self-supervised GAN attains a similar performance to state-of-the-art conditional counterparts. Finally, we show that this approach to fully unsupervised learning can be scaled to attain an FID of 33 on unconditional ImageNet generation.

Now Playing: Continuous low-power music recognition

Existing music recognition applications require a connection to a server that performs the actual recognition. In this paper we present a low-power music recognizer that runs entirely on a mobile device and automatically recognizes music without user interaction. To reduce battery consumption, a small music detector runs continuously on the mobile device's DSP chip and wakes up the main application processor only when it is confident that music is present. Once woken, the recognizer on the application processor is provided with a few seconds of audio which is fingerprinted and compared to the stored fingerprints in the on-device fingerprint database of tens of thousands of songs. Our presented system, Now Playing, has a daily battery usage of less than 1% on average, respects user privacy by running entirely on-device and can passively recognize a wide range of music.