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 11417 publications
Phoenix: Rowhammer Attacks on DDR5 with Self-Correcting Synchronization
Michele Marazzi
Kaveh Razavi
Salman Qazi
Diego Meyer
Patrick Jattke
IEEE Security & Privacy (S&P) (2026)
Preview abstract
Online video platforms face an exponential challenge
in detecting and mitigating the flood of AI-generated “slop”
and synthetic spam perpetuated by coordinated malicious actors.
This content is increasingly designed to exploit the limitations
of traditional media forensics, often utilizing generative AI to
produce unique, localized variations of harmful or low-quality
material at scale. Traditional content-centric moderation fails
against this coordinated, adversarial generation strategy.
This paper presents a novel, scalable detection and classifi-
cation framework designed for online video platforms (OVP) to
identify and triage clusters of coordinated accounts exhibiting
a prevalence of adversarial synthetic content. The approach
leverages a multi-faceted architecture incorporating two core
machine learning components: a robust Coordinated Bot-Net
Detector (via Account Relatedness) and a Synthetic Pattern Clas-
sifier. Crucially, we introduce an advanced AI enhancement layer
utilizing Large Language Models (LLMs), specialized via Low-
Rank Adaptation (LoRA) and Automatic Prompt Optimization
(APO), to achieve rapid, high-precision semantic understanding
of emerging synthetic spam trends.
Evaluated across a representative evaluation dataset (N =
16, 250 weekly candidate channels across six major synthetic
abuse verticals), the system demonstrates high precision (FPR <
0.05%) in identifying coordinated synthetic spam networks.
Furthermore, the LLM-driven classification achieves a 74%
automated triage routing rate, saving over 1, 100 operational
review hours per week while reducing investigation turnaround
times by up to 50% (p < 0.001). This work details a critical
system design that provides essential scalability and adversarial
resilience against sophisticated generative attacks.
View details
FabScore: Fine-Grained Evaluation of Fabrications in Automated AI Research
James Xu Zhao
See-Kiong Ng
Dongfu Jiang
Bryan Hooi
Qianyun Guo
Hui Chen
Pang Wei Koh
Muhao Chen
Yiwei Wang
2026
Preview abstract
In automated AI research, scientific rigor is not merely a matter of producing coherent papers and executable code; rather, it fundamentally requires that the experimental results claimed in a paper are faithfully supported by the accompanying implementation and verifiable through actual execution logs. When this alignment breaks down, AI-generated research may contain fabrications: discrepancies between the methods described in the paper and what the code actually implements, or between the reported results and those obtained by running the code. This motivates a systematic evaluation of fabrications that systematically examines the consistency between a paper's claimed experimental outcomes and its accompanying code files. In automated AI research, scientific rigor is not merely a matter of producing coherent papers and executable code; rather, it fundamentally requires that the experimental results claimed in a paper are faithfully supported by the accompanying implementation and verifiable through actual execution logs. When this alignment breaks down, AI-generated research may contain fabrications: discrepancies between the methods described in the paper and what the code actually implements, or between the reported results and those obtained by running the code. This motivates a systematic evaluation of fabrications that systematically examines the consistency between a paper's claimed experimental outcomes and its accompanying code files. This is a placeholder. This is a placeholder. This is a placeholder.
View details
AgentHands: Generating Interactive Hands Gestures for Spatially Grounded Agent Conversations in XR
Ziyi Liu
Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, ACM
Preview abstract
Communicating spatial tasks via text or speech creates ``a mental mapping gap'' that limits an agent’s expressiveness. Inspired by co-speech gestures in face-to-face conversation, we propose \textsc{AgentHands}, an LLM-powered XR system that equips agents with hands to render responses clearer and more engaging. Guided by a design taxonomy distilled from a formative study (N=10), we implement a novel pipeline to generate and render a hand agent that augments conversational responses with synchronized, space-aware, and interactive hand gestures: using a meta-instruction, \textsc{AgentHands} generates verbal responses embedded with \textit{GestureEvents} aligned to specific words; each event specifies gesture type and parameters. At runtime, a parser converts events into time-stamped poses and motions, driving an animation system that renders expressive hands synchronized with speech. In a within-subjects study (N=12), \textsc{AgentHands} increased engagement and made spatially grounded conversations easier to follow compared to a speech-only baseline.
View details
Differential Sensitivity of Impedance Plethysmography and Photoplethysmography Sensors to Temperature-Induced Peripheral Vasoconstriction
Seobin Jung
Seamus Thomson
Alexandros Pantelopoulos
Lindsey Sunden
Pete Richards
Shwetak Patel
Sam Sheng
Scientific Reports (2026)
Preview abstract
Impedance plethysmography (IPG) and photoplethysmography (PPG) are non-invasive techniques for measuring blood volume changes. This study investigated the differential responses of IPG and PPG to temperature-mediated vasoconstriction induced by localized cooling. Twenty-one participants underwent control and treatment conditions, with fake or real ice cubes applied to the forearm. Blood pressure remained stable, while heart rate decreased. PPG signal amplitude significantly decreased with cooling (p_adj = 0.004), indicating sensitivity to superficial blood flow changes. In contrast, IPG signal amplitude remained stable (p_adj = 1.0). No statistically significant differences were observed in timing-derived metrics. These findings suggest IPG is less sensitive to superficial changes in blood flow than PPG, and may be more suitable for monitoring deeper blood flow. This study provides insights into the distinct sensitivities of IPG and PPG, with implications for wearable device development and cardiovascular monitoring.
View details
Preview abstract
Source-to-source compilers may perform inefficiently by executing transpilation passes on scripts that do not contain the specific language features a pass is designed to transform, potentially leading to redundant processing. A compiler can analyze a script to generate a per-script feature map, for example, by identifying language features in its abstract syntax tree (AST). Before executing a transpilation pass, the compiler can check this map and may bypass the pass for that script if the specific feature targeted by the pass is not present. This feature map can also be dynamically updated throughout the compilation process as other passes transform the code. This method of conditional pass execution based on content-aware analysis may reduce redundant AST traversals, which could decrease overall compilation time and computational resource consumption.
View details
Expert evaluation of LLM world models: A high-Tc superconductivity case study
Haoyu Guo
Maria Tikhanovskaya
Paul Raccuglia
Alexey Vlaskin
Chris Co
Scott Ellsworth
Matthew Abraham
Lizzie Dorfman
Peter Armitage
Chunhan Feng
Antoine Georges
Olivier Gingras
Dominik Kiese
Steve Kivelson
Vadim Oganesyan
Brad Ramshaw
Subir Sachdev
Senthil Todadri
John Tranquada
Eun-Ah Kim
Proceedings of the National Academy of Sciences (2026)
Preview abstract
Large Language Models (LLMs) show great promise as a powerful tool for scientific literature exploration. However, their effectiveness in providing scientifically accurate and comprehensive answers to complex questions within specialized domains remains an active area of research. This work evaluates the performance of six different LLM-based systems for answering scientific literature questions, including commercially available closed models and a custom retrieval-augmented generation (RAG) system capable of retrieving images alongside text. We conduct a rigorous expert evaluation of the systems in the domain of high-temperature cuprate superconductors, a research area that involves material science, experimental physics, computation, and theoretical physics. We use an expert-curated database of 1726 scientific papers and a set of 67 expert-formulated questions. The evaluation employs a multi-faceted rubric assessing balanced perspectives, factual comprehensiveness, succinctness, evidentiary support, and image relevance. Our results demonstrate that RAG-based systems, powered by curated data and multimodal retrieval, outperform existing closed models across key metrics, particularly in providing comprehensive and well-supported answers, and in retrieving relevant visual information. This study provides valuable insights into designing and evaluating specialized scientific literature understanding systems, particularly with expert involvement, while also highlighting the importance of rich, domain-specific data in such 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
Preview abstract
How many T gates are needed to approximate an arbitrary n-qubit quantum state to within
a given precision ϵ? Improving prior work of Low, Kliuchnikov and Schaeffer, we show that the
optimal asymptotic scaling is Θ(sqrt{2^n log(1/ε)} + log(1/ε)) if we allow an unlimited number of ancilla qubits. We also show that this is the optimal T-count for implementing an arbitrary
diagonal n-qubit unitary to within error ϵ. We describe an application to batched synthesis of
single-qubit unitaries: we can approximate a tensor product of m = O(log log(1/ϵ)) arbitrary
single-qubit unitaries to within error ϵ with the same asymptotic T-count as is required to
approximate just one single-qubit unitary.
View details
Preview abstract
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning continue to be explored1,2. Recent reasoning-reinforced models, including OpenAI’s o-series and DeepSeek-r1, outperform other merely instruction-tuned models on complex cognitive tasks3,4, attributed to extended test-time computation through longer chains of thought5. Here we show that enhanced reasoning emerges not from extended computation alone, but from the systematic simulation of complex, multi-agent interactions—a society of thought—which enables the deliberate diversification and debate among internal cognitive perspectives characterized by distinct personality traits and domain expertise. Through quantitative analysis using classified outputs and mechanistic interpretability methods applied to reasoning traces6–8, we find that reasoning models like DeepSeek-r1 exhibit much greater perspective diversity than baseline models, activating broader and more conflict between heterogeneous personality- and expertise-related features during reasoning. This multi-agent structure manifests in conversational behaviors including question-answering sequences, perspective shifts, and reconciliation of conflicting views, as well as in socio-emotional roles that characterize back-and-forth conversation, which together account for over 60% of the accuracy advantage in reasoning tasks through both direct and indirect facilitation of cognitive strategies9,10. Controlled reinforcement learning experiments further reveal that priming models with conversational scaffolding—even when dialogues lead to incorrect solutions—substantially accelerates reasoning improvement compared to answer-only training. These findings indicate that the social organization of thought, rather than correctness alone, enables effective exploration of solution spaces. We suggest that reasoning models establish a computational parallel to collective intelligence in human groups11–13, where diversity enables superior problem-solving when systematically structured and suggest new opportunities for agent organization to harness the wisdom of crowds.
View details
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
Generational differences in anthropomorphism and trust calibration for large language models
Michelle Cohn
Joscelin Cooper
Femi Olanubi
Zion Mengesha
Frontiers in Cognition (2026)
Preview abstract
This paper examines how English-speaking adults in the United States (n=1530) anthropomorphize and calibrate trust for a pseudo-large language model (LLM). We compared four generations: Gen Z (age 18-26), Millennials (age 27-43), Gen X (age 44-57), and Baby Boomers (age 58-78). The LLM varied in cues of anthropomorphism: whether the system responded in text-only or text and speech, as well as whether it used the first-person singular (“I”) or third-person singular (“The system”) in its responses. Across both types of manipulations, results showed that Gen Z, in particular, showed consistently lower anthropomorphism (less competent, human-like, natural, conscious, life-like), reduced trust ratings of the system, and lower ratings of accuracy for responses generated by the LLM. Furthermore, we saw that the likelihood to externally validate the LLM’s response varied across the generations across contexts, where Baby Boomers were more likely to validate information about medication and health disorders and Gen Z about cooking. We did not see an interaction between the generations and the anthropomorphic cues manipulated; rather, there was a consistent increase in anthropomorphism and perceived accuracy for systems that used speech + text, relative to text only. There were no across-the-board effects of the first-person singular. We discuss these findings in terms of their implications for responsible AI.
View details
MoGen: Detailed Neuronal Morphology Generation via Point Cloud Flow Matching
Franz Rieger
International Conference on Learning Representations (ICLR) (2026)
Preview abstract
Biological neurons come in many shapes. High-fidelity generative modeling of their varied morphologies is challenging yet underexplored in neuroscience, and crucial for the subfield of connectomics. We introduce MoGen (Neuronal Morphology Generation), a flow matching model to generate high-resolution 3D point clouds of mouse cortex axon and dendrite fragments. This is enabled by an adaptation that injects local geometric context into a scalable latent transformer backbone, allowing for the generation of high-fidelity, realistic samples. To assess MoGen's generation quality, we propose a dedicated evaluation suite with interpretable geometric and topological features tailored to neuronal structures that we validate in a user study. MoGen's practical utility is showcased through controllable generation for visualization via smooth interpolation and a direct downstream application: we augment the training set of a shape plausibility classifier from a production connectomics neuron reconstruction pipeline with millions of generated samples, thereby improving classifier accuracy and reducing the number of remaining split and merge errors by 4.4%. We estimate this can reduce manual proofreading labor by over 157 person-years for reconstruction of a full mouse brain.
View details
JAXBench: Benchmarking Autonomous TPU Kernel Optimization
Vijay Janapa Reddi
Charles Hong
Arya Tschand
Julian Walker
Suvinay Subramanian
Shangkun Wang
Sethu Sankaran
Nina Cai
2026
Preview abstract
Evaluation benchmarks have driven progress in automated kernel optimization, yet existing suites target GPUs exclusively. We present JAXBench, a TPU-native benchmark for AI-generated kernel optimization on Google Cloud TPUs. JAXBench comprises 50 JAX workloads, including 17 production LLM operators extracted from architectures in the public MaxText library such as Llama-3.1, DeepSeek-V3, Mixtral, Mamba-2, and AlphaFold2, and 33 fused operator sequences adapted from KernelBench. Eight of the 17 production operators ship with hand-optimized Pallas TPU kernels from the public Tokamax library, whose block sizes we tune via grid search, establishing strong reference baselines. We evaluate one-shot generation, iterative coding agents, the same iterative loop with TPU documentation injected, and a TPU-enabled Autocomp configuration augmented with the same TPU-specific documentation. Across the full 50-benchmark suite with Gemini 3 Flash, best-of-N solves 13/50 benchmarks at 1.01x geomean and iterative refinement reaches 32/50 at 1.18x. Injecting TPU documentation lifts iterative refinement to 48/50 at 1.28x and raises per-sample correctness from 5.8% to 37.3%. Autocomp solves 45/50 but converts those correct kernels into 1.36x geomean with 76% of benchmarks beating XLA. On the 8 hand-tuned references, Autocomp reaches 1.60x against the XLA baseline, showing strong performance against the 2.08x Tokamax geomean but trailing on the specialized paged and ragged attention operators. A Gemini 3.1 Pro ablation lifts Autocomp to 49.1% per-sample correctness and a 3.13x geomean. High-quality TPU kernel generation remains open, and we release the benchmark, profiling harness, and baseline results to support reproducible research.
View details
Mind the Gap: Structure-Aware Consistency in Preference Learning
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026)
Preview abstract
Aligning Large Language Models (LLMs) with human intent, whether through explicit reward modeling or direct methods such as DPO, fundamentally relies on minimizing a surrogate loss as a proxy for the true pairwise ranking objective. We prove that this reliance is flawed for the standard surrogate losses used: for the equicontinuous hypothesis sets characteristic of neural networks, no standard surrogate provides a meaningful consistency guarantee. Minimizing the surrogate loss to zero can leave the true ranking error arbitrarily high. To resolve this, we formulate LLM alignment within a margin-shifted ranking framework and derive $H$-consistency bounds showing that enforcing a confidence margin $\gamma$ is not merely beneficial but necessary for consistency. We further introduce Structure-Aware $H$-consistency and a corresponding objective (SA-DPO) that adapts the margin to the semantic distance between responses, preventing instability on near-synonymous pairs. Finally, we analyze the trade-off between the margin required for consistency and the model's finite capacity to satisfy it, revealing a strict hierarchy of surrogate losses: heavy-tailed surrogates (e.g., the Polynomial Hinge family) offer strictly superior consistency guarantees for capacity-bounded models compared to the logistic loss used in DPO. Experiments on UltraFeedback and Argilla DPO-Mix-7k confirm that SA-DPO consistently outperforms DPO and SimPO, with a 58.5% head-to-head win-rate in downstream generation quality.
View details
