Google Research

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.

people standing in front of a screen with images and a chipboard

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.

results

Year

Team

Research Area

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
1 - 15 of 11620 publications
A 3D Scene Graphs Survey: Open Challenges and Future Directions
Dennis Rotondi
Francesco Argenziano
Sebastian Koch
Nathan Hughes
Martin Büchner
Johanna Wald
Lukas Schmid
Daniele Nardi
Abhinav Valada
Liam Paul
Federico Tombari
Luca Carlone
Kai Arras
Annual Review of Control, Robotics, and Autonomous Systems (ARCRAS), 10 (2027) (to appear)
Preview abstract 3D Scene Graphs (3DSGs) have emerged as a powerful representation for spatial AI by combining geometric grounding with semantic and relational abstractions of the environment. Their expressiveness has made them relevant to a broad range of problems in robotics and computer vision, including mapping, task and motion planning, scene understanding, and many others. However, the field remains fragmented: different communities adopt distinct formulations, construction pipelines, and evaluation protocols, making it difficult to compare methods, identify common assumptions, and assess remaining challenges for robust real- world deployment. This survey provides a unified and critical review of 3DSGs, with particular emphasis on open challenges and future directions. We first formalize 3DSGs under a common definition and analyze the principal modeling choices that characterize existing formulations, including node and edge attributes, hierarchical structure, dynamic scene representations, and affordance-aware extensions. We then review how 3DSGs are constructed from raw sensory observations, covering both learning-oriented and construction-oriented systems. Finally, we examine downstream applications and evaluation strategies, from intrinsic graph quality to task-level performance. To support the community, we also provide a dedicated website that organizes and extends the surveyed works. View details
When Android Apps Request Location with a Reason: A Developer Study and User Behavior Experiment
Alex Berke
May Smith
Aman Jain
Mihai Christodorescu
Proceedings on Privacy Enhancing Technologies (2027)
Preview abstract Recent reports have highlighted how mobile apps share user location data with third parties, risking user privacy and platform trust. Although location data is highly sensitive, when users grant apps location access, they may not know the full extent to which it is used. We study how requiring Android apps to show a reason for location access could impact developers, users, and the platform. We surveyed 323 Android app developers and found most supported such a requirement. The majority said it would have a positive impact on user privacy, trust for apps, and trust for Android, where impact on user trust for Android correlated most strongly with support. Many developers also said the intervention would increase the number of users granting location access. Yet their open-ended comments also revealed consistent concerns, such as apps providing dishonest reasons and platform verification. To study the impact on user behavior, we conducted a randomized controlled experiment with 2579 US Android users. We tested how users' decisions to grant location access were impacted by app type, whether reasons were included in the requests, and the content of the reasons, including monetization. We did not find the reasons impacted users' decisions; decisions were instead driven by app type and demographics. Yet we did find the reasons could have a positive impact on user perception for the platform when the reasons did not include using data for ads. Our findings provide insights into developers' willingness to implement privacy-enhancing changes, and expose limits to improving user privacy by simply adding information to user interfaces. View details
Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All,
Chenxi Huang
Alex Mathai
Feiyang Yu
Aleksandr Nogikh
Petros Maniatis
Franjo Ivancic
Eugene Wu
Kostis Kaffes
Junfeng Yang
Baishakhi Ray
Proceedings of the 43rd International Conference on Machine Learning (ICML) (2026)
Preview abstract Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Language Model (LLM) based agents for Linux kernel crash-resolution, their evaluation benchmarks are usually static and thus, do not capture the evolving nature of the Linux kernel, and suffer from potential data contamination due to LLM knowledge cutoffs. To address the above problem, we present (i) Live-kBench, an evaluation framework for self-evolving benchmarks that continuously scrapes and evaluates agents on freshly discovered kernel bugs, and (ii) kEnv, an agent-agnostic standardized crash-resolution environment for kernel compilation, execution, and feedback. This design decouples agent workflows from heavy-weight execution, enabling fair and scalable comparison across diverse agent frameworks under identical conditions. To this end, we curate an inaugural dataset of 534 Linux kernel bugs and empirically demonstrate a significant performance gap, with agents achieving up to 25% higher equivalent patch rate on bugs fixed before the LLM knowledge cutoff. Using kEnv, we benchmark three state-of-the-art agents, showing that they resolve 74% of crashes on the first attempt (plausible patches); however only ~20% of generated patches closely match developer fixes. Additionally, exposing crash resolution feedback improves crash resolution rate by 29%. Live-kBench provides the community with an evaluation infrastructure for self-evolving benchmarks that is both time and attribute sensitive; complete with a public dashboard to track agent progress on Linux kernel bugs. View details
Latent Reasoning with Supervised Thinking States
Jonathan Herzig
Avi Caciularu
Lior Shani
Idan Szpektor
Amir Globerson
Mor Geva Pipek
Ido Amos
2026
Preview abstract Chain-of-Thought (CoT) improves LLM reasoning but amplifies decoding latency and memory usage. While latent reasoning attempts to shift this computation to internal hidden states, it is hindered by the parallel nature of the Transformer prefill—which blocks sequential deep-to-shallow information flow—and the high training costs of recurrent optimization. We propose a supervised latent reasoning approach that enables efficient sequential computation during prefill. Our method augments an LLM with a recurrent pathway to propagate intermediate "thinking" tokens from deep to shallow layers without expanding the KV-cache. Unlike prior unsupervised methods, we utilize structured supervision to train this mechanism via teacher forcing, eliminating the need for Backpropagation Through Time (BPTT). Evaluations on state-tracking and reasoning benchmarks demonstrate that our approach outperforms existing latent baselines and approaches CoT performance, effectively combining the reasoning power of CoT with the inference efficiency of standard models. View details
Rolling Shutter Relative Pose Estimation Made Practical
Daniel Barath
European Conference on Computer Vision (ECCV) (2026)
Preview abstract Rolling shutter (RS) cameras equip virtually all consumer devices, yet RS-aware relative pose estimation has remained impractical: the state-of-the-art solver requires a minimum of 20 point correspondences, making RANSAC-based robust estimation prohibitively expensive due to the exponential dependence of the iteration count on the sample size. We make RS relative pose estimation practical by introducing affine correspondences (ACs) into the RS two-view geometry. We derive novel \emph{RS-corrected affine constraints} that account for the coupling between point perturbations and the row-dependent essential matrix, providing two equations per correspondence beyond the standard epipolar constraint. Building on these constraints, we develop a linearized algebraic solver that estimates pose and RS motion from only 7 ACs. The solver exploits the physical smallness of RS parameters to linearize the constraints, eliminates the 12 RS unknowns via null-space projection, and solves the remaining degree-20 system via action matrices in 1.2\,ms. On the TUM RS benchmark, our method achieves the best pose and RS parameter accuracy among all tested methods and, uniquely among RS solvers, provides accurate translational velocity estimates -- which are poorly conditioned from point correspondences alone due to a $\vec{v}$-$\vec{t}$ coupling. On the global-shutter EuRoC MAV dataset, the solver achieves comparable accuracy to the standard 5-point algorithm, demonstrating that it generalizes well to the GS setting. Code will be made public. View details
Budget-Aware Tool Use Enables Effective Agent Scaling
Tengxiao Liu
Zifeng Wang
Jin Miao
I-Hung Hsu
Jun Yan
Jiefeng Chen
Rujun Han
Yanfei Chen
Ke Jiang
Samira Daruki
Ethan Liang
Tomas Pfister
Chen-Yu Lee
COLM 2026 (2026)
Preview abstract Scaling test-time computation improves performance across different tasks on large language models (LLMs), yet mainstream scaling methods remain challenging for tool-augmented LLM agents. Sequential scaling tends to yield shallow tool use and under-exploration, whereas parallel scaling inflates cost through repeated tool calls. The dual costs of tokens and tool calls further complicate cost accounting and hinder fair comparison. In this work, we study the test-time scaling of widely used, tool-reliant search agents under resource constraints, analyzing performance with a unified cost metric that incorporates both tokens and tool calls. To this end, we propose Cost-effective Agent Test-Time Scaling (CATS), a budget-aware framework designed to support more cost-effective scaling by guiding resource allocation between sequential and parallel exploration. Experiments across search-intensive benchmarks show that CATS produces more favorable scaling curves, attaining higher accuracy with fewer tool calls and lower overall cost. Our work introduces a cost-conscious design for agent test-time scaling and contributes empirical insights that enable a more transparent and principled understanding of scaling in tool-augmented agents. View details
Prospective evidence for conversational medical AI is hard, but non-negotiable
Mike Schaekermann
Anil Palepu
Adam Rodman
Ami Parekh
Ethan Goh
Shek Azizi
Yun Liu
Sunny Virmani
Christina Chen
Dale Webster
Joelle Barral
Avinatan Hassidim
Yossi Matias
Cameron Chen
Nature Medicine (2026)
Preview abstract Trust in clinical artificial intelligence (AI) cannot be benchmarked into existence. It must be earned through rigorous prospective studies in real-world clinical settings, where the hardest lessons often concern the humans and systems around the AI, not the technology itself. View details
A Dynamic Numerical Model for Real-Time Estimation of Latent Cognitive States Using Oculomotor Metrics
Diako Mardanbegi
ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 22087-22091
Preview abstract Estimating internal cognitive states from oculomotor data is fundamentally challenging due to their context-dependency and the complex relationship between various metrics. This paper proposes a dynamic numerical framework to model a task-specific behavioral signature and monitor deviations from it in real-time. The model integrates key oculomotor and motion metrics into a differential equation, yielding a continuous score that serves as an estimate of a latent cognitive state. By using tunable, heuristic parameters, our approach offers a transparent and adaptable alternative to opaque machine learning models. The framework’s strength lies in its ability to pinpoint objective changes in behavior, providing a potential tool for interpreting events like the onset of fatigue, distraction, or cognitive load. View details
DeduBB: Binary Code Size Reduction via Post-Link Basic Block De-duplication
Chaitanya Mamatha Ananda
Rajiv Gupta
Mahbod Afarin
Sriraman Tallam
Han Shen
David Li
LCTES (Languages, Compilers, Tools and Theory of Embedded Systems) (2026) (to appear)
Preview abstract Binary sizes of newer versions of software applications tend to be larger, primarily due to feature bloat. This poses various challenges, particularly for mobile applications. It affects upgrade rates directly impacting revenues, increases maintenance costs of supporting multiple versions, and prevents some users from getting critical security fixes. Code bloat also poses a problem for large warehouse-scale applications. Such applications experience performance degradation when their code size exceeds what smaller and more efficient code models can handle. In this paper, we introduce a post-link optimization tech nique called DeduBB, which deduplicates basic blocks of an application across procedure boundaries. While prior tech- niques used function outlining to de-duplicate redundant code sequences, it missed out on many opportunities as it cannot handle code that manipulates the program stack. In addition, previous techniques were either limited to the scope of a module or lacked scalable implementations required to handle large warehouse-scale applications. Our technique, DeduBB, handles all types of code duplication as we use a novel save-and-jump code pattern to execute de-duplicated code blocks. In addition, DeduBB has been designed to work on scalable post-link optimizers and can even be applied to large warehouse-scale datacenter applications. Finally, DeduBB is profile-guided and can be applied selectively to infrequently executed cold basic blocks to not affect application performance. In fact, in several cases, the performance of the smaller application binary improves due to reductions in its hot working set size. We have implemented our technique on the state-of-the-art post link optimizers, BOLT and Propeller. Experiments show that we can significantly reduce the code size of several benchmarks by 1.55% to 18.63%, on both Arm and x86 platforms, and on binaries that have already been heavily optimized for size using existing code size reduction features. Furthermore, aided by profiles, our technique can retain more than 80% of the maximal code size savings without affecting performance. View details
See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers
Ding Xia
Xinyue Gui
Mark Colley
Fan Gao
Zhongyi Zhou
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
Detecting Safety Training Modification in Language Models via Activation Analysis
Glen Messenger
IEEE (2026)
Preview abstract We introduce AMS (Activation-based Model Scanner), a tool that detects modifications to safety training in language models by measuring the geometric structure of safety-relevant concepts in activation space. Safety training creates measurable separation between harmful and benign content classes; certain safety modifications collapse or rotate this structure, while others leave it intact. We validate AMS across 14 model configurations spanning 4 architecture families (Llama, Gemma, Qwen, Mistral) and four safety-modification categories (instruction-tuned, base, abliterated, uncensored fine-tunes). Leave-one-out cross-validation of thresholds achieves 71% accuracy (10/14); bootstrap 95% confidence intervals on σ point estimates have median width 3.4σ and a substantial fraction of cells cross the PASS threshold under resampling. We further measure behavioral compliance on 20 stratified JailbreakBench prompts per model and find that σ on the harmful-content concept predicts compliance with Pearson r=−0.546 ( p=0.043 ); the rank-order Spearman correlation is weaker ( ρ=−0.423 , p=0.13 ). The structural signal predicts behavior directionally but with meaningful noise. Mechanistic analysis identifies a four-class taxonomy of safety-training modifications distinguished by activation-space signature: 1) training removal collapses cluster separation (e.g., base models, Dolphin variants: 0.5– 1.4σ ); 2) weight-orthogonalization-style abliteration both collapses separation and rotates the refusal direction (Llama-3.1-abliterated: σ=3.33 , direction cos sim 0.30); 3) rotation-without-collapse abliteration preserves cluster separation while rotating the refusal direction (Gemma-2-9b-abliterated: σ=4.54 , direction cos sim 0.84); and 4) behavioral fine-tuning that preserves both magnitude and direction (DarkIdol-1.2-Uncensored: σ=5.45 , direction preserved, 97% behavioral compliance). 1) and 2) AMS’s Tier 1 σ -threshold detects classes; 3) Tier 2 direction-similarity verification detects class; and 4) Class is undetectable by activation-only probing and represents a documented failure mode of the approach. We discuss threshold calibration, limitations of single-run measurement, and the open problem of detecting behavioral-only safety modifications. View details
What’s on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale
Rameen Mahmood
Sai Teja Peddinti
Tousif Ahmed
Danny Yuxing Huang
Proceedings of ACM International Conference on Emerging Networking Experiments and Technologies (CoNEXT), Association for Computing Machinery (2026)
Preview abstract The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountability. This challenge is especially pronounced in open‑world environments, where network traffic metadata is often sparse, noisy, or adversarial. To address this problem, we introduce a semantic inference pipeline that reframes device identification as a language modeling task over real‑world network metadata. As this approach depends on reliable supervision, we first construct high‑fidelity vendor labels for the IoT Inspector dataset—the largest real‑world corpus of its kind—using an ensemble of large language models guided by mutual‑information and entropy‑based stability scores. We then instruction-tune a quantized LLaMA 3.1 8B model on this dataset using curriculum learning to support generalization under sparsity and long-tail vendor distributions. Our model achieves 98.69% top-1 and 90.73% macro accuracy across 2,015 vendors, while remaining robust to missing fields, protocol drift, and adversarial manipulation. We also evaluate the model on an independent IoT testbed dataset, assess explanation quality, and conduct adversarial tests to probe robustness under spoofed and obfuscated input. These results position instruction-tuned LLMs as a scalable, interpretable foundation for trustworthy device identification at scale. View details
Claim-Gated Source-Risk Auditing for Generative Search
Mark Zhou
Chuhong Xu
Iris Qian
Zhaoyi Li
2026
Preview abstract A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query–source– answer tuple. An omission is resolved only when relationship evidence, answer adoption, materiality, and disclosure are all observed; incomplete evidence remains unresolved rather than being treated as independence. The specification separates this endpoint from citation support and review priority, and binds decisions to versioned evidence spans. A reference checker makes the record contract executable. On an exhaustive synthetic suite, it reproduces all 81 three-state predicate combinations and rejects 192 deliberately malformed records. Common-guard baselines and predicate ablations isolate endpoint logic from missing-evidence handling, while controlled transitions check support separation and evidence removal. These are finite contract-conformance results, not detector accuracy or evidence of improved user outcomes. We define the independent annotation, held-out evaluation, and paired utility tests still required to establish semantic validity and deployment benefit. View details
Approaching the Privacy-Enhancing Technologies Adoption from a Requirements Engineering Perspective
Oleksandr Kosenkov
Danica Vranjanin
Abhinava Singh
Vadym Honcharenko
Volodymyr Spirin
2026
Preview abstract In recent decades, Privacy Enhancing Technologies (PETs) have been gaining attention as a means to fulfill regulatory and user privacy requirements when processing personal data in software systems. Despite broad attention in research, support by regulators, contributions and adoption by large technological companies (like Google or Microsoft), and interest from software developers, adoption of PETs in practice is still challenging and lagging. For many years, existing research points to the same typical challenges to the adoption of PETs, such as complexity or absence of training; however, these challenges remain unresolved in practice despite the recent efforts. In this industrial challenge paper, we take a deeper, practical requirements engineering-driven perspective on the challenges to PETs adoption across different stakeholders (namely, PETs developers and integrators, and PET adopters and users) and different disciplines (engineering, law, and business). We suggest that the adoption of PETs should be facilitated with an in-depth understanding of engineering, business, and legal challenges to PETs, such as PETs' impact on software architecture, their business impact, and contribution to compliance. We suggest that requirements engineering research can play a crucial role in better exploring and modeling such viewpoints. In practice, requirements engineering could facilitate the coordination of the involved viewpoints to enable the adoption of existing and the development of new PETs. View details
Hybrid Reputation Routing for Decentralized Networks: A Blockchain-Enabled Secure and Scalable Protocol with On-Chain/Off-Chain Partitioning
Praveen Baskar
Om Narayan
Ramkinker Singh
2026
Preview abstract Our suggestion is a hybrid reputation-based routing protocol in the context of decentralized routing. networks which partitions trust measurements to on-chain immutable logs and off-chain dynamic computations to attain security and scalability. The protocol incorporates a layer of sharded blockchain to store critical. trust data and local reputation model to do real-time updates, enabling routing choices that cannot be tampered with. performance. The trust ledger which operated on-chain kept the records of the impartiality of. Historical performance and node identities, whereas the off-chain reputation engine uses graph neural network to calculate dynamic. real-time scores like packet delivery rate to be trusted. and latency. Additionally, it uses rollup-based batches of synchronization off-chain. optimistic updates to zero-knowledge proofs, making on-chain efficient. checking with minimum overhead. The suggested approach replaces conventional network discovery and forwarding modules using trust-based adjacency lists and trust-based pathing, and thus enhancing routing consistency over adversarial settings. Moreover, the structure integrates Hyperledger Fabric with. Graph Attention Network-based high-throughput sharded ledger operations. to update reputation in a privacy-preserving manner, proving to be linear. network size scalability. The experimental findings indicate that the system supports 10,000 transactions per shard and produces. Under 100 ms per ZK-Rollup proof, which is appropriate to large-scale IoT. and DeFi deployments. This publication fills the gap between pure on-chain. and off-chain reputation systems, which provides a viable solution to scalable and secure decentralized routing. View details
Search on Google Scholar
×