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 11420 publications
In Search of "Weird Corners": Diagnosing the Limits of Convergent AI in Professional Creative Practice
Mark Williams
2026
Preview abstract
Generative AI assistants typically employ convergent interaction paradigms to resolve ambiguity. While effective for technical tasks, this risks premature convergence in creative domains, constraining output variance. Evaluating a convergent AI probe with expert creatives (N=9) indicates an interactional paradox: structural linearity provides "ignition" utility for early ideation, but misaligns with organic workflows, often inducing "aesthetic sanitization" that standardizes individualized nuance. Prioritizing constructive friction over default agreement, the experts requested active, lateral collaborators. In response, we reframe output convergence as a "full-stack" UI challenge, advocating for Generative frameworks that operationalize the Double Diamond via fluid role-shifting and productive tension.
View details
Cost-effective Agent Test-Time Scaling
Samira Daruki
I-Hung Hsu
Jin Miao
Tengxiao Liu
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
Preview abstract
Modern user interfaces are complex composites, with elements originating from various sources, such as the operating system, apps, a web browser, or websites. Many security and privacy models implicitly depend on users correctly identifying an element's source, a concept we term ''surface attribution.'' Through two large-scale vignette-based surveys (N=4,400 and N=3,057), we present the first empirical measurement of this ability.
We find that users struggle, correctly attributing UI source only 55% of the time on desktop and 53% on mobile. Familiarity and strong brand cues significantly improve accuracy, whereas UI positioning, a long-held security design concept especially for browsers, has minimal impact. Furthermore, simply adding a ''Security & Privacy'' brand cue to Android permission prompts failed to improve attribution. These findings demonstrate a fundamental gap in users' mental models, indicating that relying on them to distinguish trusted UI is a fragile security paradigm.
View details
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
Dj Dvijotham
Mirko Montanari
ACL 2026
Preview abstract
Artificial intelligence is rapidly evolving, marked by the emergence of Large Language Model (LLM) agents – systems capable of complex reasoning, planning, and interaction with digital and physical environments. These agents, powered by advancements in LLMs, demonstrate remarkable capabilities across diverse domains, including finance, healthcare, web navigation, software development, and daily task assistance. Unlike traditional AI systems, LLM agents can perceive their surroundings, formulate multi-step plans, utilize external tools and APIs, access memory or knowledge bases, and execute actions to achieve specified goals. This ability to act upon the world, however, introduces significant safety and security challenges.
The safety paradigms developed for traditional LLMs, primarily focused on mitigating harmful textual outputs (e.g., toxicity, bias), are insufficient for safeguarding LLM agents. Agents interacting with dynamic environments and executing actions present a broader attack surface and new categories of risk. These include performing unsafe operations, violating privacy constraints through improper data handling or access control failures, deviating from user objectives (task misalignment), and susceptibility to novel manipulation techniques like indirect prompt injection and memory poisoning. Ensuring the trustworthy operation of these powerful agents is paramount, especially as they are integrated into high-stakes applications. To address this critical challenge, we introduce VeriGuard, a novel framework designed to enhance the safety and reliability of LLM agents by interactively verifying their policies and the actions. VeriGuard integrates a verification module that intercepts code-based actions proposed by the agent. In the first step, VeriGuard will generates and verifies the policies. The policies are rigorously checked against a set of predefined safety and security specifications Then each action will be verified to make sure it will align with the agent specification. This interactive verification loop ensures that the agent's behavior remains within safe operational bounds, effectively preventing the execution of harmful or unintended operations. By verifying each step, VeriGuard provides a robust safeguard, substantially improving the trustworthiness of LLM agents in complex, real-world environments.
View details
Type-Aware Ranking of Urban Similarity from Aerial Imagery
Idan Kligvasser
Yotam Intrator
Yuval Desheh
Aviad Barzilai
Niv Efron
Ehud Rivlin
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops (2026), pp. 821-829
Preview abstract
Estimating and ranking cross-city similarity from aerial imagery is a fundamental challenge in remote sensing and geospatial representation learning. Urban environments differ widely in road layout, marking conventions, and infrastructure design, yet standard visual representations often struggle to disentangle these meaningful structural variations from superficial appearances. In this work, we propose a type-aware contrastive learning framework that measures urban similarity by explicitly modeling distinct infrastructure elements. Leveraging open-vocabulary retrieval, we construct a globally diverse dataset of road-related features, such as intersections, crosswalks, and bus lanes, and train a type-conditioned Vision Transformer that fuses visual features with CLIP-derived semantic embeddings. Crucially, we introduce an adaptive per-type contrastive loss that dynamically emphasizes infrastructure categories with high discriminative power while down-weighting less informative types. To quantify city-level similarity, we aggregate per-type cosine similarities via a lightweight classifier to generate a global city-to-city similarity matrix. Experiments demonstrate that this type-aware approach significantly improves clustering quality and successfully generalizes to unseen cities, establishing a scalable, interpretable foundation for comparative urban analysis.
View details
Visual Planning: Let’s Think Only with Images
Han Zhou
Caiqi Zhang
Anna Korhonen
Chengzu Li
Yi Xu
Ivan Vulic
International Conference on Learning Representations (ICLR) (2026)
Preview abstract
Recent advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have significantly enhanced machine reasoning across diverse tasks. However, these models predominantly rely on language as the medium for both expressing and structuring reasoning, even when visual information is present. In this work, we argue that language may not always be the most natural or effective modality for reasoning, particularly in tasks involving spatial, geometric, or physical dynamics. Motivated by this, we propose a new paradigm, Visual Planning, which enables planning through purely visual representations, independent of textual mediation. In this paradigm, planning is executed via sequences of images that encode step-by-step inference in the visual domain, akin to how humans sketch or visualize future actions. We then introduce a novel two-stage reinforcement learning framework empowered by GRPO for post-training large vision models, resulting in substantial improvements in planning accuracy and generalization across both seen and novel scenarios, validated in representative visual navigation tasks, FrozenLake and Maze. Our results establish Visual Planning as a viable and promising alternative to language-based reasoning, opening new avenues for tasks that benefit from intuitive, image-based inference.
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
Performance and User Response of Android's Smartphone-Based Alerts in the 2025 Marmara Ereğlisi Earthquake
Marc Stogaitis
Youngmin Cho
Richard Allen
Boone Spooner
Patrick Robertson
Greg Wimpey
Robert Bosch
Nivetha Thiruverahan
Steve Malkos
Alexei Barski
Tajinder Gadh
Nature Communications (2026)
Preview abstract
This study presents a comprehensive evaluation of Google’s Android Earthquake Alert (AEA) system during the Mw 6.2 Marmara Ereğlisi, Türkiye earthquake. AEA detected the event 5.31 seconds after its initiation, alerting over 16 million users. Warning times for weak shaking (MMI III) reached up to 150 seconds, with a median of 56 seconds. While near-source warning windows were shorter, the system achieved 90% true positives and 99% precision overall. The high density of the phone network enabled faster detection than traditional stations, even for this offshore epicenter. Feedback data shows AEA recipients were highly likely to take protective actions, such as "drop, cover, and hold on," or warn others. Timely alerts substantially increased user engagement, perceived usefulness, and future trust. These results highlight how crowd-sourced technology and behavioral insights can effectively enhance seismic resilience on a massive scale.
View details
Preview abstract
We study the stochastic linear bandits with parameter noise model, in which the reward of action $a$ is $a^\top \theta$ where $\theta$ is sampled i.i.d.
We show a regret upper bound of $\tO \brk{\sqrt{d T \logKdelta \sigmax}}$ for a horizon $T$, general action set of size $K$ of dimension $d$, and where $\sigmax$ is the maximal variance of the reward for any action.
We further provide a lower bound of $\tOmega \brk{d \sqrt{T \sigmax}}$ which is tight (up to logarithmic factors) whenever $\log \brk{K} \approx d$.
For more specific action sets, $\ell_p$ unit balls with $p \leq 2$ and dual norm $q$, we show that the minimax regret is $\tTheta \brk{\sqrt{dT \vsigq}}$, where $\vsigq$ is a variance-dependent quantity that is always at most $4$.
This is in contrast to the minimax regret attainable for such sets in the classic additive noise model, where the regret is of order $d \sqrt{T}$.
Surprisingly, we show that this optimal (up to logarithmic factors) regret bound is attainable using a very simple explore-exploit algorithm.
View details
Observing long-lived longwave contrail forcing
Aarón Sonabend
Joe Ng
Atmospheric Measurement Techniques (2026)
Preview abstract
Contrail microphysical simulations and climate simulations have indicated that contrail cirrus cause a substantial fraction of aviation’s climate impact. While the approximations and parameter selections in these simulations have been well-validated over the past two decades, the heat trapping of contrails has not been observed using satellite data beyond a few hours. This is because contrails lose their linear shape after a few hours, making them difficult to distinguish from natural cirrus clouds. Here we provide satellite-driven analysis of long-lived heat trapping by contrails over North and South America. We aggregate a dataset of GOES-16 estimated outgoing longwave radiation and advected trace density of flight paths, and apply causal inference to discern the effect of contrails while controlling for radiative and cloud confounders. As a means of validation, we also generate synthetic datasets with known ground truth, and confirm that applying the causal inference method is able to recover the synthetic ground truth. Since this method yields an estimate which has some differences from both “instantaneous radiative forcing” (iRF) and “effective radiative forcing” (ERF) estimates which have been reported in the literature so far, we introduce the new term “observational radiative forcing, 12 hours” (oRF12). Our analysis estimates the longwave oRF12 from contrails over the Americas averaged 47.9 gigajoules per flight kilometer (95% CI: 31 to 52 GJ/km) during April 2019 to April 2020.
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
KVCIS: Activation-Based Token Importance Prediction for Intelligent KV-Cache Compression
Zenodo (2026)
Preview abstract
We introduce KVCIS (KV-Cache Importance Scoring), a novel approach to KV-cache compression that predicts token importance from intermediate-layer activations before attention is computed. Unlike existing methods (H2O, StreamingLLM, Scissorhands) that make compression decisions based on attention scores computed during generation, KVCIS enables proactive compression at cache insertion time—determining how to store each token before paying the computational cost of attention. We discover a two-level importance structure in decoder-only transformers: the beginning-of-sequence (BOS) token acts as an "attention sink" receiving ~76% of attention, while the remaining ~24% is distributed across content tokens with 10-11× importance spread. A simple linear probe achieves R² = 0.998 overall and R² = 0.68–0.79 for discriminating among content tokens. Extensive validation across 3 model families (Llama, Mistral, Gemma), 8 layer depths, context lengths from 256 to 2048 tokens, and multiple downstream tasks demonstrates: 50% memory reduction with zero degradation on NarrativeQA (F1 = 0.064 matching baseline exactly), while uniform quantization degrades by 7.8% at the same compression ratio. KVCIS consistently achieves 5–8× better quality preservation than uniform quantization across all tested context lengths. The memory savings enable increased batch sizes and longer context support; the probe itself adds minimal overhead (~16KB direction vector, 0.06ms per token). This work extends activation-based probing from safety classification to inference optimization, demonstrating that intermediate-layer activations encode predictive signals about token importance for generation.
View details
Preview abstract
This paper demonstrates that artificial intelligence can accelerate mathematical discovery by autonomously solving an open problem in theoretical physics. We present a neuro-symbolic system, combining the Gemini Deep Think large language model with a systematic Tree Search (TS) framework and automated numerical feedback, that successfully derived novel, exact analytical solutions for the power spectrum of gravitational radiation emitted by cosmic strings. Specifically, the agent evaluated the core integral for arbitrary loop geometries, directly improving upon recent AI-assisted attempts that only yielded partial asymptotic solutions. To substantiate our methodological claims regarding AI-accelerated discovery and to ensure transparency, we detail system prompts, search constraints, and intermittent feedback loops that guided the model. The agent identified a suite of 6 different analytical methods, the most elegant of which expands the kernel in Gegenbauer polynomials to naturally absorb the integrand's singularities. The methods lead to an asymptotic result for at large that both agrees with numerical results and also connects to the continuous Feynman parameterization of Quantum Field Theory. We detail both the algorithmic methodology that enabled this discovery and the resulting mathematical derivations.
View details
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
AI, Identity, and Ethical Governance: Building Trust in High-Stakes Systems
Ibrahim Waziri Jr.
Abhilasha Bhargav - Spantzel
RSAC (2026)
Preview abstract
As AI redefines identity verification in high stakes systems, it introduces novel risks like deepfake fraud and algorithmic bias, creating a critical trust deficit. This session will provide a practical framework for ethical governance, equipping leaders to build and manage secure, fair, and fundamentally trustworthy AI systems by design.
View details
