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 11367 publications
Taming the Variants Multi-Architecture Continuous Testing at Google
Chandrakanth Chittappa
Ali Esmaeeli
Laura Macaddino
Sam Manfreda
David Margolin
Dharma Naidu
Sabuj Pattanayek
Sachin Sable
Ruslan Sakevych
Dushyant Acharya
Adrian Berding
Kevin Crossan
Wolff Dobson
Abhay Singh
19th IEEE International Conference on Software Testing, Verification and Validation (ICST) 2026, Daejeon, Republic of Korea, IEEE
Preview abstract
Enterprises are increasingly adopting multiple general-purpose computer architectures in the data center. This leads to new testing challenges as it creates demand to qualify the software for the additional architectures. Naively double-testing all software for both architectures is costly and unnecessary. Further, reconfiguring CI/CD to take advantage of the new architecture can be non-trivial at scale. This paper introduces CI/CD variants and an optimized testing cycle to solve these twin challenges. We empirically evaluate our solution's impact on human and machine expenses using 44k projects at Google on real production data. First, we estimate saving ~25% of machine expenses at the negligible cost of a few delayed breakage detections per day. Second, we estimate a 90+% reduction in human cost for migrating the configuration. All features described in this paper are now Generally Available at Google and we report this as an empirical case study in scaling CI/CD to new architectures.
View details
Bridging the Dimensionality Gap: A Taxonomy and Survey of 2D Vision Model Adaptation for 3D Analysis
Preview abstract
The remarkable success of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in 2D computer vision has catalyzed significant research into their adaptation for the complex domain of 3D analysis. However, a fundamental dichotomy exists between the regular, dense grid of 2D images and the irregular, sparse nature of 3D data formats such as point clouds and meshes. This paper provides a comprehensive survey and a novel intellectual framework for navigating this burgeoning field. Our core contribution is a new taxonomy that organizes adaptation strategies into three distinct families: (1) Data-centric methods, which project 3D data into 2D formats to leverage off-the-shelf 2D models; (2) Architecture-centric methods, which design intrinsic network modules to directly process 3D data; and (3) Hybrid methods, which synergistically combine pre-trained 2D features with 3D modeling processing pipelines to benefit from both rich visual priors and explicit geometric reasoning. Through this taxonomic lens, we conduct a systematic review and qualitative synthesis of the field. We illuminate the fundamental trade-offs between these families concerning computational complexity, reliance on large-scale pre-training, and the preservation of geometric inductive biases. Based on this analysis, we identify and discuss critical open challenges and chart promising future research directions, including the development of 3D foundation models, advancements in self-supervised learning for geometric data, and the deeper integration of multi-modal signals. This survey serves as an essential resource and roadmap for researchers seeking to understand and advance the state-of-the-art in 3D computer vision.
View details
Nudging Developers Toward Privacy: Evaluating the Impact of Personalized App Review Reports
Omer Akgul
Michelle L. Mazurek
USENIX Symposium on Usable Privacy and Security (SOUPS) (2026)
Preview abstract
Mobile application developers often struggle to create accurate privacy notices or implement robust privacy practices due to limited expertise or resources. While users share unsolicited privacy feedback in app reviews, and prior research has characterized this privacy feedback, uncovering developer reactions to this feedback remains unexplored. This study explores whether personalized privacy review reports---summarizing real user feedback for a developer's own app---can effectively nudge them toward planning privacy improvements. We surveyed 42 app developers, presenting them with reports containing privacy themes, temporal trends, peer benchmarks, and emotion distributions derived from their apps' reviews. Our findings indicate that these privacy report interventions proved highly effective, with 76% (32 of 42) of participants finding at least one section of the report useful. Furthermore, exposure to the report increased the participants' intent to pursue privacy-relevant actions -- such as reorganizing the UI, enhancing privacy communications, or adding/removing features -- with 69% (29 of 42) of participants indicating an increased intent to do so. Almost all developers expressed a desire to receive such privacy reports periodically or on demand. These results indicate that making this style of report broadly available across the industry could foster a more privacy-conscious mobile ecosystem.
View details
An experimental evaluation of an AI-powered interactive learning platform
Nicole Miller
Yael Haramaty
Lidan Hackmon
Lior Belinsky
Abraham Oritz Tapia
Lucy Tootill
Scott Siebert
Frontiers in Artificial Intelligence (2026) (to appear)
Preview abstract
Generative AI, which is capable of transforming static content into dynamic learning experiences, holds the potential to revolutionize student engagement in educational contexts. However, questions still remain around whether or not these tools are effective at facilitating student learning. In this research, we test the effectiveness of an AI-powered platform incorporating multiple representations and assessment through Learn Your Way, an experimental research platform that transforms textbook chapters into dynamic visual and audio representations. Through a between-subjects, mixed methods experiment with 60 US-based students, we demonstrate that students who used Learn Your Way had a more positive learning experience and had better learning outcomes compared to students learning the same content through a digital textbook. These findings indicate that AI-driven tools, capable of providing choice among interactive representations of content, constitute an effective and promising method for enhancing student learning.
View details
Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
Pengfei He
Ash Fox
Stefan Friedli
Daniel Fabian
Burak Gokturk
Jiliang Tang
ICML 2026
Preview abstract
Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of experience reuse. We propose Code-RedTeam, a security-aware multi-agent framework designed to mirror real-world red-teaming workflows by integrating security-domain knowledge, code-aware analysis, execution-grounded iterative reasoning, and long-term memory. Code-RedTeam decomposes vulnerability analysis into coordinated discovery and exploitation stages, enabling agents to plan, execute, validate, and refine actions based on real execution feedback while learning from prior trajectories. Extensive evaluations on challenging security benchmarks demonstrate that Code-RedTeam consistently outperforms strong baselines across diverse backbone models, achieving over 60% attack success rate in vulnerability exploitation and up to 10% absolute improvement in vulnerability detection. Ablation and iteration studies further confirm the critical role of execution feedback, structured interaction, and memory for building robust and generalizable cybersecurity agents.
View details
Preview abstract
Generative AI is reshaping software development, yet its psychological impact remains under-researched. During May and August 2025 we conducted reflexive thematic analysis of interviews with 12 senior engineers (≥5 years experience) recruited from Western technology hubs to explore shifts in professional identity. We identify a central transition from "coder to conductor," where AI acts as a cognitive partner. Key findings include: (1) a re-architecting of focus from implementation to strategy; (2) a shift in productivity metrics from output to impact; and (3) a dual-impact on agency, where AI empowers autonomy but threatens competence through de-skilling anxieties. These findings suggest that as implementation becomes commoditised, organisational training and career progression must prioritise architectural mastery and metacognitive oversight to ensure sustained developer motivation and system integrity.
View details
Preview abstract
Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most appearing infrequently. While scaling has improved average-case performance, persistent failures on low-frequency, domain-specific, cultural, and temporal knowledge remain poorly characterized. This paper develops a structured taxonomy and analysis of long-tail knowledge in large language models, synthesizing prior work across technical and sociotechnical perspectives.
We organize the literature along four complementary axes: how long-tail knowledge is defined, the mechanisms by which it is lost or distorted during training and inference, the technical interventions proposed to mitigate these failures, and the implications of these failures for fairness, accountability, transparency, and user trust. We further examine how existing evaluation practices obscure tail behavior and complicate accountability for rare but consequential failures. The paper concludes by identifying open challenges related to privacy, sustainability, and governance that constrain long-tail knowledge representation. Taken together, this paper provides a unifying conceptual framework for understanding how long-tail knowledge is defined, lost, evaluated, and manifested in deployed language model systems.
View details
Preview abstract
We study the fair allocation of indivisible goods with variable groups. In this model, the goal is to partition the agents into groups of given sizes and allocate the goods to the groups in a fair manner. We show that for any number of groups and corresponding sizes, there always exists an envy-free up to one good (EF1) outcome, thereby generalizing an important result from the individual setting. Our result holds for arbitrary monotonic utilities and comes with an efficient algorithm. We also prove that the EF1 existence can be guaranteed even when the goods lie on a path and each group must receive a connected bundle. In addition, we consider a probabilistic model where the utilities are additive and drawn randomly from a distribution. We show that if there are n agents and the number of goods m is divisible by the number of groups k, then an envy-free outcome exists with high probability if m = ω(log n), and this bound is tight. On the other hand, if m is not divisible by k, then an envy-free outcome is unlikely to exist as long as m = o(√n).
View details
Preview abstract
Multimodal large language models (LLMs) integrate and process information from multiple modalities such as text, images, audio, and video, enabling complex tasks such as audio translation and visual question answering. While powerful, this complexity introduces novel vulnerabilities to sophisticated adversarial attacks. This survey paper provides a comprehensive overview of this rapidly expanding field, systematically categorizing attacks that range from manipulations of single modalities (e.g., perturbed images or audio) to those exploiting cross-modal interactions. We overview how these attacks exploit weaknesses in model fusion, attention mechanisms, and representation learning and provided analyses on their potential for real-world consequences.
View details
Preview abstract
We introduce AASE (Activation-based AI Safety Enforcement), a framework for post-perception safety monitoring in large language models. Unlike pre-perception approaches that analyze input or output text, AASE monitors the model's internal activation patterns—what the model "understands" rather than what text it processes or generates—enabling detection of safety-relevant states before harmful outputs are produced. The framework comprises three techniques: Activation Fingerprinting (AF) for harmful content detection, Agent Action Gating (AAG) for prompt injection defense, and Activation Policy Compliance (APC) for enterprise policy enforcement. We introduce paired contrastive training to isolate safety-relevant signals from confounding factors such as topic and style, addressing signal entanglement in polysemantic activations. Validation across 7 models from 3 architecture families shows strong class separation: Gemma-2-9B achieves AUC 1.00 with 7.2σ separation across all probes; AAG achieves AUC ≥0.88 across all models on the InjecAgent benchmark; APC achieves 0.97-1.00 AUC across three enterprise policies. Model size correlates with probe quality—Gemma-2-9B (7.2σ separation) outperforms Gemma-2-2B (4.3σ). All techniques survive INT4 quantization with minimal separation degradation. AASE is 9× faster than Llama Guard 3 (33ms vs 306ms) with higher TPR (88% vs 50%) at a tunable threshold that trades FPR for detection sensitivity, adding only 0.002ms probe overhead to existing inference.
View details
Preview abstract
In today's AI landscape, success depends not just on prompting large language models but on orchestrating them into intelligent systems that are scalable, compliant, and cost-effective. GenAI on Google Cloud is your hands-on guide to bridging that gap. Whether you're an ML engineer or an enterprise leader, this book offers a practical game plan for taking agentic systems from prototype to production.
Written by practitioners with deep experience in AgentOps, data engineering, and GenAI infrastructure, this guide takes you through real-world workflows from data prep and deployment to orchestration and integration. With concrete examples, field-tested frameworks, and honest insights, you'll learn how to build agentic systems that deliver measurable business value.
> Bridge the production gap that stalls 90% of vertical AI initiatives using systematic deployment frameworks
> Navigate AgentOps complexities through practical guidance on orchestration, evaluation, and responsible AI practices
> Build robust multimodal systems for text, images, and video using proven agent architectures
> Optimize for scale with strategies for cost management, performance tuning, and production monitoring
View details
See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers
Ding Xia
Xinyue Gui
Mark Colley
Fan Gao
Dongyuan Li
Renhe Jiang
Takeo Igarashi
ACL 26 (2026)
Preview abstract
Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language models (VLMs) for perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of \systemName for scalable action design.
View details
SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
Jian Zhang
Bangya Liu
Achuta Kadambi
Zhiwen Fan
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)
Preview abstract
Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial relationships. While recent efforts have introduced multi-view geometry transformers into VLMs, they typically fuse only the deep-layer features from vision and geometry encoders, discarding rich hierarchical signals and creating a fundamental bottleneck for spatial understanding. To overcome this, we propose SpatialStack, a general hierarchical fusion framework that progressively aligns vision, geometry, and language representations across the model hierarchy. Moving beyond conventional late-stage vision-geometry fusion, SpatialStack stacks and synchronizes multi-level geometric features with the language backbone, enabling the model to capture both local geometric precision and global contextual semantics. Building upon this framework, we develop VLM-SpatialStack, a model that achieves state-of-the-art performance on multiple 3D spatial reasoning benchmarks. Extensive experiments and ablations demonstrate that our multi-level fusion strategy consistently enhances 3D understanding and generalizes robustly across diverse spatial reasoning tasks, establishing SpatialStack as an effective and extensible design paradigm for vision-language-geometry integration in next-generation multimodal physical AI systems.
View details
Preview abstract
We introduce a new context-enriched time series forecasting benchmark TimesX. TimesX contains a wide selection of high-quality real-world time series and diverse textual contexts from an automated generating pipeline, which helps address three main issues of existing benchmarks: (1) poor generalization due to low data volume and data being synthetic, (2) restricted forms of context, and (3) an inability to mitigate data leakage. We conduct a thorough empirical study of current multimodal solutions on TimesX. Our results suggest that most multimodal solutions that work well on existing benchmarks may fail on TimesX. In contrast, simple ensemble methods that leverage the rich textual context can outperform strong unimodal baselines and other multimodal baselines.
** Below this is what was submitted to ITP. **
We create a real world multimodal time-series forecasting benchmark that encompasses diverse domains and regions. Each time-series is annotated by various kinds of contexts like metadata, date and holiday information, dynamic events related to the time-series. This is sufficiently more advanced than other available benchmarks which rely wither on static metadata alone or synthetic examples. This forms a test bed for multimodal forecasting. We also present some baseline results showing that ensembles of publicly available LLMs and time-series foundation models can demonstrate non-trivial performance on this bechmark.
View details
Towards A Human-in-the-Loop Framework for Reliable Patch Evaluation using an LLM-as-a-Judge
Sherry Shi
Renyao Wei
Michele Tufano
José Cambronero
Runxiang Cheng
AI-SQE '26: Proceedings of the 1st International Workshop on AI for Software Quality Evaluation - Judgment, Metrics, Benchmarks, and Beyond, ACM (Association for Computing Machinery), New York, NY, USA (2026), pp. 19 - 28
Preview abstract
Reliable evaluation is crucial for advancing Automated Program Repair (APR), but prevailing benchmarks that rely on execution-based evaluation methods (pass@k) often fail to capture the patch quality required for real-world adoption. This creates a significant gap between automated metrics and true patch validity (valid@k), a discrepancy observed across several state-of-the-art techniques.
To develop a scalable solution for measuring valid@k, we first study the human evaluation process itself. While manual assessment can determine validity, we find it suffers from poor inter-rater reliability (Fleiss' Kappa k=0.307). Our foundational insight is that this inconsistency is largely resolved when evaluators use a shared, high-quality rubric, which significantly improves agreement.
Building on this finding, we propose an LLM-as-a-Judge framework that operationalizes rubric-guided evaluation at scale. Our method employs a human-in-the-loop workflow where an LLM first generates a candidate rubric for a given bug, which a human expert then reviews and refines into a "golden" evaluation standard. This golden rubric is then used by an LLM judge to assess the validity of candidate patches. In an evaluation on 48 bugs and 115 patches, our LLM judge demonstrates substantial agreement with the consensus of human developers. This work contributes a scalable and reliable methodology for approximating valid@k, providing a much-needed high-fidelity signal for measuring true progress in the field of automated program repair.
View details
