Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10100 publications
Preview abstract
Computing efficient traffic signal plans is often based on the amount of traffic in an intersection, its distribution over the various intersection movements and hours as well as on performance metrics such as traffic delay. In their simple and typical form plans are fixed in the same hour over weekdays. This allows low operation costs without the necessity for traffic detection and monitoring tools. A critical factor on the potential efficiency of such plans is the similarity of traffic patterns over the days along each of the intersection movements. We refer to such similarity as the traffic stability of the intersection and define simple metrics to measure it based on traffic volume and traffic delay. In this paper, we propose an automatic probe data based method, for city-wide estimation of traffic stability. We discuss how such measures can be used for signal planning such as in selecting plan resolution or as an indication as which intersections can benefit from dynamic but expensive traffic detection tools. We also identify events of major changes in traffic characteristics of an intersection. We demonstrate the framework by using real traffic statistics to study the traffic stability in the city of Haifa along its 162 intersections. We study the impact of the time of day on the stability, detect major changes in traffic and find intersections with high and low stability.
View details
Hovering Over the Key to Text Input in XR
Diar Abdlkarim
Arpit Bhatia
Stuart Macgregor
Jason Fotso-Puepi
Hasti Seifi
Massimiliano Di Luca
Karan Ahuja
Preview abstract
Virtual, Mixed, and Augmented Reality (XR) technologies hold immense potential for transforming productivity beyond PC. Therefore there is a critical need for improved text input solutions for XR. However, achieving efficient text input in these environments remains a significant challenge. This paper examines the current landscape of XR text input techniques, focusing on the importance of keyboards (both physical and virtual) as essential tools. We discuss the unique challenges and opportunities presented by XR, synthesizing key trends from existing solutions.
View details
Preview abstract
We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data. We synthesize a large dataset of image captions using LLMs, then use an off-the-shelf text-to-image model to generate multiple images corresponding to each synthetic caption. We perform visual representation learning on these synthetic images via contrastive learning, treating images sharing the same caption as positive pairs. The resulting representations transfer well to many downstream tasks, competing favorably with other general-purpose visual representation learners such as CLIP and DINO v2 in image classification tasks. Furthermore, in dense prediction tasks such as semantic segmentation, SynCLR outperforms previous self-supervised methods by a significant margin, e.g., improving over MAE and iBOT by 6.2 and 4.3 mIoU on ADE20k for ViT-B/16.
View details
Rich Human Feedback for Text to Image Generation
Katherine Collins
Nicholas Carolan
Youwei Liang
Peizhao Li
Dj Dvijotham
Gang Li
Sarah Young
Jiao Sun
Arseniy Klimovskiy
Preview abstract
Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality.
Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior work collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation.
In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which keywords in the text prompt are not represented in the image.
We collect such rich human feedback on 18K generated images and train a multimodal transformer to predict these rich feedback automatically.
We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions.
Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants).
View details
Preview abstract
We present Prequal (\emph{Probing to Reduce Queuing and Latency}), a load balancer
for distributed multi-tenant systems. Prequal aims to minimize
real-time request latency in the presence of heterogeneous server
capacities and non-uniform, time-varying antagonist load. It actively probes
server load to leverage the \emph{power of $d$ choices}
paradigm, extending it with asynchronous and reusable probes. Cutting
against received wisdom, Prequal does not balance CPU load, but instead
selects servers according to estimated latency and active requests-in-flight
(RIF). We explore its major design features on a testbed system
and evaluate it on YouTube, where it has been deployed for more than two years. Prequal has dramatically decreased tail latency, error rates, and resource use, enabling YouTube and
other production systems at Google to run at much higher utilization.
View details
Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines
Aditya U Kale
Alastair Dennison
Alexander Martindale
An Wen Chan
Andrew Beam
Benjamin Ng
Cecilia S. Lee
Christopher Yau
David Moher
Gary Collins
Lauren Oakden-Rayner
Lavinia Ferrante di Ruffano
Melanie Calvert
Melissa D McCradden
Pearse Keane
Robert Golub
Samantha Cruz Rivera
Victoria Ngai
Xiaoxuan Liu
Nature Communications (2024)
Preview abstract
The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77–94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.
View details
Preview abstract
New regulations and increased awareness of data privacy have led to the deployment of new and more efficient differentially private mechanisms across public institutions and industries. Ensuring the correctness of these mechanisms is therefore crucial to ensure the proper protection of data. However, since differential privacy is a property of the mechanism itself, and not of an individual output, testing whether a mechanism is differentially private is not a trivial task. While ad hoc testing techniques exist under specific assumptions, no concerted effort has been made by the research community to develop a flexible and extendable tool for testing differentially private mechanisms. This paper introduces DP-Auditorium as a step advancing research in this direction. DP-Auditorium abstracts the problem of testing differential privacy into two steps: (1) measuring the distance between distributions, and (2) finding neighboring datasets where a mechanism generates output distributions maximizing such distance. From a technical point of view, we propose three new algorithms for evaluating the distance between distributions. While these algorithms are well-established in the statistics community, we provide new estimation guarantees that exploit the fact that we are only interested in verifying whether a mechanism is differentially private, and not in obtaining an exact estimate of the distance between two distributions. DP-Auditorium is easily extensible, as demonstrated in this paper by implementing a well-known approximate differential privacy testing algorithm into our library. We provide an extensive comparison to date of multiple testers across varying sample sizes and differential privacy parameters, demonstrating that there is no single tester that dominates all others, and that a combination of different techniques is required to ensure
proper testing of mechanisms.
View details
Making Images from Images: Tightly Constrained Parallel Denoising
Ashwin Baluja
European Conference on Computer Vision, AI for Visual Arts Workshop and Challenges (2024)
Preview abstract
We present methods to transform an image into a novel one of any subject matter simply by rearranging the image’s tiles. Our method extends and improves recent work in the generation of optical illusions by discovering the optimal arrangement of the image’s tiles simultaneously with the image generation. In addition to producing images that more accurately represent the subject matter, this technique allows us to address a much broader class of problems than previously possible. By learning the image transforms, we allow any source image to be pre- specified; any existing image (e.g. the Mona Lisa) can be transformed to a novel subject. We formulate this as a tightly constrained optimization problem and address it through alternating the steps of image diffusion and energy minimization using optimal matching. Under our formulation, a simple method to extend this to infinite copies of the source image is also given. Unlike previous methods, as the number of tiles grows the problem becomes easier and the results become better.
View details
Experiencing InstructPipe: Building Multi-modal AI Pipelines via Prompting LLMs and Visual Programming
Zhongyi Zhou
Jing Jin
Xiuxiu Yuan
Jun Jiang
Jingtao Zhou
Yiyi Huang
Kristen Wright
Jason Mayes
Mark Sherwood
Ram Iyengar
Na Li
Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems, ACM, pp. 5
Preview abstract
Foundational multi-modal models have democratized AI access, yet the construction of complex, customizable machine learning pipelines by novice users remains a grand challenge. This paper demonstrates a visual programming system that allows novices to rapidly prototype multimodal AI pipelines. We first conducted a formative study with 58 contributors and collected 236 proposals of multimodal AI pipelines that served various practical needs. We then distilled our findings into a design matrix of primitive nodes for prototyping multimodal AI visual programming pipelines, and implemented a system with 65 nodes. To support users' rapid prototyping experience, we built InstructPipe, an AI assistant based on large language models (LLMs) that allows users to generate a pipeline by writing text-based instructions. We believe InstructPipe enhances novice users onboarding experience of visual programming and the controllability of LLMs by offering non-experts a platform to easily update the generation.
View details
Preview abstract
2022 marked the 50th anniversary of memory safety vulnerabilities, first reported by Anderson et al. Half a century later, we are still dealing with memory safety bugs despite substantial investments to improve memory unsafe languages.
Like others', Google’s data and internal vulnerability research show that memory safety bugs are widespread and one of the leading causes of vulnerabilities in memory-unsafe codebases. Those vulnerabilities endanger end users, our industry, and the broader society.
At Google, we have decades of experience addressing, at scale, large classes of vulnerabilities that were once similarly prevalent as memory safety issues. Based on this experience we expect that high assurance memory safety can only be achieved via a Secure-by-Design approach centered around comprehensive adoption of languages with rigorous memory safety guarantees.
We see no realistic path for an evolution of C++ into a language with rigorous memory safety guarantees that include temporal safety. As a consequence, we are considering a gradual transition of C++ code at Google towards other languages that are memory safe.
Given the large volume of pre-existing C++, we believe it is nonetheless necessary to improve the safety of C++ to the extent practicable. We are considering transitioning to a safer C++ subset, augmented with hardware security features like MTE.
View details
Preview abstract
Specialized Large multi-modal models (LMMs) have exhibited remarkable performance across numerous tasks, however, generalist LMMs suffer from performance degradation when training with a large collection of tasks. Recent research suggests Mixture of Experts (MoE) Models help instruction tuning, however, for LMMs of parameter size around O(50-100B), the prohibitive cost of replicating and storing the expert models severely limits the number of experts we can use.
We propose Omni-SMoLA that softly mixes many multimodal low rank experts to large models without introducing significant new parameter count compared to conventional MoE models. The core idea is that the large model provides a foundational backbone and different lightweight experts learn specialized knowledge residually. Extensive experiments demonstrate that the SMoLA approach helps improve the generalist performance across a broad range of visual question answering and captioning tasks, achieving a new state-of-the-art generalist performance that matches or outperforms single specialized LMM baselines.
View details
Preview abstract
In this paper we study users' opinions about the privacy of their mobile health apps. We look at what they write in app reviews in the 'Health & Fitness' category on the Google Play store. We identified 2832 apps in this category (based on 1K minimum installs). Using NLP/LLM analyses, we find that 76% of these apps have at least some privacy reviews. In total this yields over 164,000 reviews about privacy, from over 150 countries and in 25 languages. Our analyses identifies top themes and offers an approximation of how widespread these issues are around the world. We show that the top 4 themes - Data Sharing and Exposure, Permission Requests, Location Tracking and Data Collection - are issues of concern in over 70 countries. Our automatically generated thematic summaries reveal interesting aspects that deserve further research around user suspicions (unneeded data collection), user requests (more fine-grained control over data collection and data access), as well as user behavior (uninstalling apps).
View details
Preview abstract
Knowledge-grounded dialogue generation is a challenging task because it requires satisfying two fundamental yet often competing constraints: being responsive in a manner that is specific to what the conversation partner has said while also being attributable to an underlying source document. In this work, we bring this trade-off between these two objectives (specificity and attribution) to light and ask the question: Can explicit content planning before the response generation help the model to address this challenge? To answer this question, we design a framework called PLEDGE, which allows us to experiment with various plan variables explored in prior work, supporting both metric-agnostic and metric-aware approaches. While content planning shows promise, our results on whether it can actually help to navigate this trade-off are mixed -- planning mechanisms that are metric-aware (use automatic metrics during training) are better at automatic evaluations but underperform in human judgment compared to metric-agnostic mechanisms. We discuss how this may be caused by over-fitting to automatic metrics and the need for future work to better calibrate these metrics towards human judgment. We hope the observations from our analysis will inform future work that aims to apply content planning in this context.
View details
Preview abstract
Interactions with Extended Reality Head Mounted Devices (XR HMDs) applications require precise, intuitive and efficient input methods. Current approaches either rely on power-intensive sensors, such as cameras for hand-tracking, or specialized hardware in the form of handheld controllers. As an alternative, past works have explored the use of devices already present with the user, in the form of smartphones and smartwatches as practical input solutions. However, this approach risks interaction overload---how can one determine whether the user’s interaction gestures on the watch-face or phone screen are directed toward control of the mobile device itself or the XR device? To this effect, we propose a novel framework for cross-device input routing and device arbitration by employing Inertial Measurement Units (IMUs) within these devices. We validate our approach in a user study with six participants. By making use of the relative orientation between the headset and the target input device, we can estimate the intended device of interaction with 93.7% accuracy. Our method offers a seamless, energy-efficient alternative for input management in XR, enhancing user experience through natural and ergonomic interactions.
View details
Preview abstract
The effect of regularizers such as weight decay when training deep neural networks is not well understood. We study the influence of weight decay as well as $L2$-regularization when training neural network models in which parameter matrices interact multiplicatively. This combination is of particular interest as this parametrization is common in attention layers, the workhorse of transformers. Here, key-query, as well as value-projection parameter matrices, are multiplied directly with each other: $W_K^TW_Q$ and $PW_V$.
We extend previous results and show on one hand that any local minimum of a $L2$-regularized loss of the form $L(AB^\top) + \lambda (\|A\|^2 + \|B\|^2)$ coincides with a minimum of the nuclear norm-regularized loss $L(AB^\top) + \lambda\|AB^\top\|_*$, and on the other hand that the 2 losses become identical exponentially quickly during training. We thus complement existing works linking $L2$-regularization with low-rank regularization, and in particular, explain why such regularization on the matrix product affects early stages of training.
Based on these theoretical insights, we verify empirically that the key-query and value-projection matrix products $W_K^TW_Q, PW_V$ within attention layers, when optimized with weight decay, as usually done in vision tasks and language modelling, indeed induce a significant reduction in the rank of $W_K^TW_Q$ and $PW_V$, even in fully online training.
We find that, in accordance with existing work, inducing low rank in attention matrix products can damage language model performance, and observe advantages when decoupling weight decay in attention layers from the rest of the parameters.
View details
