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 10330 publications
Preview abstract
Measuring productivity is equivalent to building a model. All models are wrong, but some are useful. Productivity models are often “worryingly selective” (wrong because of omissions). Worrying selectivity can be combated by taking a holistic approach that includes multiple measurements of multiple outcomes. Productivity models should include multiple outcomes, metrics, and methods.
View details
Context is Key for Agent Security
Lillian Tsai
Eugene Bagdasaryan
arXiv (2025)
Preview abstract
Judging the safety of an action, whether taken by a human or a system, must take into account the context in which the action takes place. For example, deleting an email from a user's mailbox may or may not be appropriate depending on the email's content, the user's goals, or even available space. Systems today that make these judgements---providing security against harmful or inappropriate actions---rely on manually-crafted policies or user confirmation for each relevant context. With the upcoming deployment of systems like generalist agents, we argue that we must rethink security designs to adapt to the scale of contexts and capabilities of these systems. As a first step, this paper explores contextual security in the domain of agents and proposes contextual security for agents (Conseca), a framework to generate just-in-time, contextual, and human-verifiable security policies.
View details
From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
Han Zhou
Ke Jiang
International Conference on Learning Representations (ICLR) (2025) (to appear)
Preview abstract
Recent advances in long-context large language models (LLMs) have led to the emerging paradigm of many-shot in-context learning (ICL), where it is observed that scaling many more demonstrating examples beyond the conventional few-shot setup in the context can lead to performance benefits. However, despite its promise, it is unclear what aspects dominate the benefits and whether simply scaling to more examples is the most effective way of improving many-shot ICL. In this work, we first provide an analysis of the factors driving many-shot ICL, and we find that 1) many-shot performance can still be attributed to often a few disproportionately influential examples and 2) identifying such influential examples ("optimize") and using them as demonstrations to regenerate new examples ("generate") can lead to further improvements. Inspired by the findings, we propose BRIDGE, an algorithm that alternates between the optimize step with Bayesian optimization to discover the influential sets of examples and the generate step to reuse this set to expand the reasoning paths of the examples back to the many-shot regime automatically. On Gemini, Claude, and Mistral LLMs of different sizes, we show that BRIDGE to significant improvements across a diverse set of tasks, including symbolic reasoning, numerical reasoning, and code generation.
View details
Preview abstract
https://www.overleaf.com/project/65ba7d45dae2bce751dba252
Hashing is a fundamental operation in various computer sci-
ence applications. Despite the prevalence of specific key
formats like social security numbers, MAC addresses, plate
numbers, and URLs, hashing libraries typically treat them as
general byte sequences. This paper introduces a technique
for synthesizing specialized hash functions tailored to par-
ticular byte formats. The proposed code generation method
leverages three prevalent patterns: (i) fixed-length keys, (ii)
keys with common subsequences, and (iii) keys ranging on
predetermined sequences of bytes. The code generation pro-
cess involves two algorithms: one identifies relevant regular
expressions within key examples, and the other generates
specialized hash functions based on these expressions. This
approach, straightforward to implement, showcases improve-
ments over highly optimized hash function implementations.
Comparative analysis demonstrates that our synthetic func-
tions outperform counterparts in the C++ Standard Template
Library and the Google Abseil Library, achieving speedups
ranging from 2% to 11%, depending on the key format.
View details
Heterogenous graph neural networks for species distribution modeling
Christine Kaeser-Chen
Keith Anderson
Michelangelo Conserva
Elise Kleeman
Maxim Neumann
Matt Overlan
Millie Chapman
Drew Purves
arxiv (2025)
Preview abstract
Species distribution models (SDMs) are necessary for measuring and predicting occurrences and habitat suitability of species and their relationship with environmental factors. We introduce a novel presence-only SDM with graph neural networks (GNN). In our model, species and locations are treated as two distinct node sets, and the learning task is predicting detection records as the edges that connect locations to species. Using GNN for SDM allows us to model fine-grained interactions between species and the environment. We evaluate the potential of this methodology on the six-region dataset compiled by National Center for Ecological Analysis and Synthesis (NCEAS) for benchmarking SDMs. For each of the regions, the heterogeneous GNN model is comparable to or outperforms previously-benchmarked single-species SDMs as well as a feed-forward neural network baseline model.
View details
Preview abstract
Storage on Android has evolved significantly over the years, with each new Android version introducing changes aimed at enhancing usability, security, and privacy. While these updates typically help with restricting app access to storage through various mechanisms, they may occasionally introduce new complexities and vulnerabilities. A prime example is the introduction of scoped storage in Android 10, which fundamentally changed how apps interact with files. While intended to enhance user privacy by limiting broad access to shared storage, scoped storage has also presented developers with new challenges and potential vulnerabilities to address. However, despite its significance for user privacy and app functionality, no systematic studies have been performed to study Android’s scoped storage at depth from a security perspective. In this paper, we present the first systematic security analysis of the scoped storage mechanism. To this end, we design and implement a testing tool, named ScopeVerif, that relies on differential analysis to uncover security issues and implementation inconsistencies in Android’s storage. Specifically, ScopeVerif takes a list of security properties and checks if there are any file operations that violate any security properties defined in the official Android documentation. Additionally, we conduct a comprehensive analysis across different Android versions as well as a cross-OEM analysis to identify discrepancies in different implementations and their security implications. Our study identifies both known and unknown issues of scoped storage. Our cross-version analysis highlights undocumented changes as well as partially fixed security loopholes across versions. Additionally, we discovered several vulnerabilities in scoped storage implementations by different OEMs. These vulnerabilities stem from deviations from the documented and correct behavior, which potentially poses security risks. The affected OEMs and Google have acknowledged our findings and offered us bug bounties in response.
View details
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren
Jianyi Zhang
Chun-Sung Ferng
Ankur Taly
International Conference on Learning Representations (ICLR) (2025)
Preview abstract
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context from retrieval or the context itself is insufficient to answer the query. To shed light on this, we develop a new notion of sufficient context, along with a method to classify instances that have enough information to answer the query. We then use sufficient context to analyze several models and datasets. By stratifying errors based on context sufficiency, we find that larger models with higher baseline performance (Gemini 1.5 Pro, GPT 4o, Claude 3.5) excel at answering queries when the context is sufficient, but often output incorrect answers instead of abstaining when the context is not. On the other hand, smaller models with lower baseline performance (Llama 3.1, Mistral 3, Gemma 2) hallucinate or abstain often, even with sufficient context. We further categorize cases when the context is useful, and improves accuracy, even though it does not fully answer the query and the model errs without the context. Building on our findings, we explore ways to reduce hallucinations in RAG systems, including a new selective generation method that leverages sufficient context information for guided abstention. Our method improves the fraction of correct answers among times where the model responds by 2--10% for Gemini, GPT, and Gemma.
View details
Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
Mauro Comi
Max Yang
Jonathan Tremblay
Valts Blukis
Yijiong Lin
Nathan Lepora
Laurence Aitchison
2025
Preview abstract
Touch and vision go hand in hand, mutually enhancing our ability to understand the world. From a research perspective, the problem of mixing touch and vision is underexplored and presents interesting challenges. To this end, we propose Tactile-Informed 3DGS, a novel approach that incorporates touch data (local depth maps) with multi-view vision data to achieve surface reconstruction and novel view synthesis. Our method optimises 3D Gaussian primitives to accurately model the object's geometry at points of contact. By creating a framework that decreases the transmittance at touch locations, we achieve a refined surface reconstruction, ensuring a uniformly smooth depth map. Touch is particularly useful when considering non-Lambertian objects (e.g. shiny or reflective surfaces) since contemporary methods tend to fail to reconstruct with fidelity specular highlights. By combining vision and tactile sensing, we achieve more accurate geometry reconstructions with fewer images than prior methods. We conduct evaluation on objects with glossy and reflective surfaces and demonstrate the effectiveness of our approach, offering significant improvements in reconstruction quality.
View details
Mufu: Multilingual Fused Learning for Low- Resource Translation with LLM
Zheng Lim
Honglin Yu
Trevor Cohn
International Conference on Learning Representations (ICLR) 2025
Preview abstract
Multilingual large language models (LLMs) are great translators, but this is largely limited to high-resource languages. For many LLMs, translating in and out of low-resource languages remains a challenging task. To maximize data efficiency in this low-resource setting, we introduce Mufu, which includes a selection of automatically generated multilingual candidates and an instruction to correct inaccurate translations in the prompt. Mufu prompts turn a translation task into a postediting one, and seek to harness the LLM's reasoning capability with auxiliary translation candidates, from which the model is required to assess the input quality, align the semantics cross-lingually, copy from relevant inputs and override instances that are incorrect. Our experiments on En-XX translations over the Flores-200 dataset show LLMs finetuned against Mufu-style prompts are robust to poor quality auxiliary translation candidates, achieving performance superior to NLLB 1.3B distilled model in 64% of low- and very-low-resource language pairs. We then distill these models to reduce inference cost, while maintaining on average 3.1 chrF improvement over finetune-only baseline in low-resource translations.
View details
Circadian rhythm of heart rate and activity: a cross-sectional study
Maryam Khalid
Logan Schneider
Aravind Natarajan
Conor Heneghan
Karla Gleichauf
Chronobiology International (2025)
Preview abstract
ABSTRACT
Background: Circadian rhythms are commonly observed in a number of physiological processes. Consumer wearable devices have made it possible to obtain continuous time series data from a large number of individuals. We study circadian rhythms from measurements of heart rate, movement, and sleep, from a cohort of nearly 20,000 participants over the course of 30 days.
Methods: Participation was restricted to Fitbit users of age 21 years or older residing in the United States or Canada. Participants were enrolled through a recruitment banner shown on the Fitbit App. The advertisement was shown to 531,359 Fitbit users, and 23,239 enrolled in the program. Of these, we obtained heart rate data from 19,350 participants. We obtain the underlying circadian rhythm from time series heart rate by modeling the circadian rhythm as a sum over the first two Fourier harmonics. The first Fourier harmonic accounts for the 24-hour rhythmicity, while the second harmonic accounts for non-sinusoidal perturbations.
Findings: We observe a circadian rhythm in both heart rate and acceleration. From the diurnal modulation, we obtain the following circadian parameters: (i) amplitude of modulation, (ii) bathyphase, (iii) acrophase, (iv) non-sinusoidal fraction, and (v) fraction of day when the heart rate is greater than the mean. The amplitude, bathyphase, and acrophase depend on sex, and decrease with age. The waketime on average, follows the bathyphase by 2.4 hours. In most individuals, the circadian rhythm of heart rate lags the circadian rhythm of activity.
Interpretation: Circadian metrics for heart rate and activity can be reliably obtained from commercially available wearable devices. Distributions of circadian metrics can be valuable tools for individual-level interpretation.
View details
Enhancing Remote Sensing Representations through Mixed-Modality Masked Autoencoding
Ori Linial
Yochai Blau
Nadav Sherman
Yotam Gigi
Wojciech Sirko
Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops (2025), pp. 507-516
Preview abstract
This paper presents an innovative approach to pre-training models for remote sensing by integrating optical and radar data from Sentinel-2 and Sentinel-1 satellites. Using a novel variation on the masked autoencoder (MAE) framework, our model incorporates a dual-task setup: reconstructing masked Sentinel-2 images and predicting corresponding Sentinel-1 images. This multi-task design enables the encoder to capture both spectral and structural features across diverse environmental conditions. Additionally, we introduce a "mixing" strategy in the pretraining phase, combining patches from both image sources, which mitigates spatial misalignment errors and enhances model robustness. Evaluation on segmentation and classification tasks, including Sen1Floods11 and BigEarthNet, demonstrates significant improvements in adaptability and generalizability across varied downstream remote sensing applications. Our findings highlight the advantages of leveraging complementary modalities for more resilient and versatile land cover analysis.
View details
Scaling Laws for Downstream Task Performance in Machine Translation
Natalia Ponomareva
Hussein Hazimeh
Sanmi Koyejo
International Conference on Learning Representations (ICLR) (2025) (to appear)
Preview abstract
Scaling laws provide important insights that can guide the design of large language models (LLMs). Existing work has primarily focused on studying scaling laws for pretraining (upstream) loss. However, in transfer learning settings, in which LLMs are pretrained on an unsupervised dataset and then finetuned on a downstream task, we often also care about the downstream performance. In this work, we study the scaling behavior in a transfer learning setting, where LLMs are finetuned for machine translation tasks. Specifically, we investigate how the choice of the \emph{pretraining} data and its size affect downstream performance (translation quality) as judged by: downstream cross-entropy and translation quality metrics such as BLEU and COMET scores. Our experiments indicate that the size of the finetuning dataset and the distribution alignment between the pretraining and downstream data significantly influence the scaling behavior. With sufficient alignment, both downstream cross-entropy and translation quality scores improve monotonically with more pretraining data. In such cases, we show that it is possible to predict the downstream translation quality metrics with good accuracy using a log-law. However, there are cases where moderate misalignment causes the downstream translation scores to fluctuate or get worse with more pretraining, whereas downstream cross-entropy monotonically improves. By analyzing these, we provide new practical insights for choosing appropriate pretraining data.
View details
Preview abstract
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context from retrieval or the context itself is insufficient to answer the query. To shed light on this, we develop a new notion of sufficient context, along with a way to classify instances that have enough information to answer the query. We then use sufficient context to analyze several models and datasets. By stratifying errors based on context sufficiency, we find that proprietary LLMs (Gemini, GPT, Claude) excel at answering queries when the context is sufficient, but often output incorrect answers instead of abstaining when the context is not. On the other hand, open-source LLMs (Llama, Mistral, Gemma) hallucinate or abstain often, even with sufficient context. We further categorize cases when the context is useful, and improves accuracy, even though it does not fully answer the query and the model errs without the context. Building on our findings, we explore ways to reduce hallucinations in RAG systems, including a new selective generation method that leverages sufficient context information for guided abstention. Our method improves the fraction of correct answers among times where the model responds by 2--10% for Gemini, GPT, and Gemma.
View details
Preview abstract
Unifying query languages is key in reducing toil for app developers and end users to query and analyze observability data. A common query language that can leverage all observability data such as metrics, traces, profiles, events, logs to facilitate correlation, support trend analytics and provide end-to-end observability for AI applications. The Observability TAG QLS workgroup is finalizing a semantic query language spec in 2025 and is recommending SQL as a basis with further experimentation on syntaxes. This talk will explore the design principles, user research and challenges of creating a query language to support observability goals. It will delve into the core concepts, syntax, and semantics of SQL operators and its needed syntactic sugar, while addressing the unique requirements of observability data. It will also explore the trade-offs between simplicity, expressiveness, and performance. This query language convergence for end-to-end analytics could enhance reliability and operational efficiency for SREs and your app developers. A win-win for all.
View details
Preview abstract
Project estimation is a crucial aspect of project management that is often fraught with uncertainty. Accurately predicting project costs, timelines, and potential risks is essential for successful project delivery and eventually the program success which comprises several focused projects. Program Evaluation and Review Technique (PERT) is a valuable tool for addressing these challenges by providing a structured approach to project scheduling and risk assessment. Hopfield networks are a type of recurrent neural network with a rich history in the field of artificial intelligence particularly for their role in associative memory and optimization tasks. This paper delves into the potential application of Hopfield networks in PERT analysis, exploring practical implementations, challenges and strategies for overcoming limitations to enhance project and program management outcomes.
View details