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 10497 publications
Preview abstract
Understanding fine-grained temporal dynamics is crucial in egocentric videos, where continuous streams capture frequent, close-up interactions with objects. In this work, we bring to light that current egocentric video question-answering datasets often include questions that can be answered using only few frames or commonsense reasoning, without being necessarily grounded in the actual video. Our analysis shows that state-of-the-art Multi-Modal Large Language Models (MLLMs) on these benchmarks achieve remarkably high performance using just text or a single frame as input. To address these limitations, we introduce EgoTempo, a dataset specifically designed to evaluate temporal understanding in the egocentric domain. EgoTempo emphasizes tasks that require integrating information across the entire video, ensuring that models would need to rely on temporal patterns rather than static cues or pre-existing knowledge. Extensive experiments on EgoTempo show that current MLLMs still fall short in temporal reasoning on egocentric videos, and thus we hope EgoTempo will catalyze new research in the field and inspire models that better capture the complexity of temporal dynamics. Dataset and code are available at https://github.com/google-research-datasets/egotempo.git.
View details
Heterogeneous 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
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
Preview abstract
Data science, which transforms raw data into actionable insights, is critical for data-driven decision-making. However, these tasks are often complex, involving steps like exploring multiple data sources and synthesizing findings to deliver clear answers. While large language model (LLM) agents show significant promise in automating this process, they often struggle with heterogeneous data formats and generate sub-optimal analysis plans, as verifying plan correctness is inherently difficult without ground-truth labels for such open-ended tasks. To overcome these limitations, we introduce DS-STAR, a novel data science agent. Specifically, DS-STAR makes three key contributions: (1) a data file analysis module that automatically reads and extracts context from diverse data formats, including unstructured types; (2) a verification step where an LLM-based judge evaluates the sufficiency of the analysis plan at each stage; and (3) a sequential planning mechanism that starts with a simple, executable plan and iteratively refines it based the DS-STAR's feedback until its sufficiency is confirmed. This iterative refinement allows DS-STAR to reliably navigate complex analyses involving varied data sources. Our experiments show that DS-STAR achieves state-of-the-art performance, improving accuracy on the challenging DABStep benchmark from 41.0% to 45.2% and on Kramabench from 31.3% to 44.7%. These results demonstrate the effectiveness of our approach for practical, multi-step data science tasks.
View details
Capturing Real-World Habitual Sleep Patterns with a Novel User-centric Algorithm to Pre-Process Fitbit Data in the All of Us Research Program: Retrospective observational longitudinal study
Hiral Master
Jeffrey Annis
Karla Gleichauf
Lide Han
Peyton Coleman
Kelsie Full
Neil Zheng
Doug Ruderfer
Logan Schneider
Evan Brittain
Journal of Medical Internet Research (2025)
Preview abstract
Background:
Commercial wearables such as Fitbit quantify sleep metrics using fixed calendar times as default measurement periods, which may not adequately account for individual variations in sleep patterns. To address this limitation, experts in sleep medicine and wearable technology developed a user-centric algorithm designed to more accurately reflect actual sleep behaviors and improve the validity of wearable-derived sleep metrics.
Objective:
This study aims to describe the development of a new user-centric algorithm, compare its performance with the default calendar-relative algorithm, and provide a practical guide for analyzing All of Us Fitbit sleep data on a cloud-based platform.
Methods:
The default and user-centric algorithms were implemented to preprocess and compute sleep metrics related to schedule, duration, and disturbances using high-resolution Fitbit sleep data from 8563 participants (median age 58.1 years, 6002/8341, 71.96%, female) in the All of Us Research Program (version 7 Controlled Tier). Variations in typical sleep patterns were calculated by examining the differences in the mean number of primary sleep logs classified by each algorithm. Linear mixed-effects models were used to compare differences in sleep metrics across quartiles of variation in typical sleep patterns.
Results:
Out of 8,452,630 total sleep logs collected over a median of 4.2 years of Fitbit monitoring, 401,777 (4.75%) nonprimary sleep logs identified by the default algorithm were reclassified as primary sleep by the user-centric algorithm. Variation in typical sleep patterns ranged from –0.08 to 1. Among participants with the greatest variation in typical sleep patterns, the user-centric algorithm identified significantly more total sleep time (by 17.6 minutes; P<.001), more wake after sleep onset (by 13.9 minutes; P<.001), and lower sleep efficiency (by 2.0%; P<.001), on average. Differences in sleep stage metrics between the 2 algorithms were modest.
Conclusions:
The user-centric algorithm captures the natural variability in sleep schedules, providing an alternative approach to preprocess and evaluate sleep metrics related to schedule, duration, and disturbances. A publicly available R package facilitates the implementation of this algorithm for clinical and translational research.
View details
DroidCCT: Cryptographic Compliance Test via Trillion-Scale Measurement
Preview
Rémi Audebert
Pedro Barbosa
Borbala Benko
Alex (Mac) Mihai
László Siroki
Catherine Vlasov
Annual Computer Security Applications Conference (ACSAC) (2025) (to appear)
Passive Heart Rate Monitoring During Smartphone Use in Everyday Life
Shun Liao
Paolo Di Achille
Jiang Wu
Silviu Borac
Jonathan Wang
Eric Teasley
Lawrence Cai
Daniel McDuff
Hao-Wei Su
Brent Winslow
Anupam Pathak
Shwetak Patel
Jim Taylor
Jamie Rogers
(2025)
Preview abstract
Resting heart rate (RHR) is an important biomarker of cardiovascular health and mortality, but tracking it longitudinally generally requires a wearable device, limiting its availability. We present PHRM, a deep learning system for passive heart rate (HR) and RHR measurements during ordinary smartphone use, using facial video-based photoplethysmography. Our system was developed using 225,773 videos from 495 participants and validated on 185,970 videos from 205 participants in laboratory and free-living conditions – the largest validation study of its kind. Compared to reference electrocardiogram, PHRM achieved a mean absolute percentage error (MAPE) <10% for HR measurements across three skin tone groups of light, medium and dark pigmentation; MAPE for each skin tone group was non-inferior versus the others. Daily RHR measured by PHRM had a mean absolute error <5 bpm compared to a wearable HR tracker, and was associated with known risk factors. These results highlight the potential of smartphones to enable passive and equitable heart health monitoring.
View details
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
Diganta Misra
Nizar Islah
Brice Rauby
Zihan Wang
Justine Gehring
Antonio Orvieto
Muawiz Chaudhary
Eilif Muller
Irina Rish
Samira Ebrahimi Kahou
Massimo Caccia
2025
Preview abstract
The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent version updates while preserving backward compatibility. While existing code evolution benchmarks provide valuable insights, they typically lack execution-based evaluation for generating code compliant with specific library versions. To address this, we introduce GitChameleon 2.0, a novel, meticulously curated dataset comprising 328 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. GitChameleon 2.0 rigorously evaluates the capacity of contemporary large language models (LLMs), LLM-powered agents, code assistants, and RAG systems to perform version-conditioned code generation that demonstrates functional accuracy through execution. Our extensive evaluations indicate that state-of-the-art systems encounter significant challenges with this task; enterprise models achieving baseline success rates in the 48-51% range, underscoring the intricacy of the problem. By offering an execution-based benchmark emphasizing the dynamic nature of code libraries, GitChameleon 2.0 enables a clearer understanding of this challenge and helps guide the development of more adaptable and dependable AI code generation methods.
View details
Mix&Slice
Marco Rosa
Encyclopedia of Cryptography, Security and Privacy, Springer Nature Switzerland (2025), pp. 1550-1555
Preview abstract
Mix&Slice is an encryption technique that enables efficient and robust access revocation on resources stored at external cloud providers. The technique makes use of a transformation that provides strong inter-dependency in the encrypted representation of a resource. To perform access revocation, it is then sufficient to re-encrypt a small portion of the resource to have guarantees that the resource (and any of its parts) will become unintelligible to those from whom access has been revoked.
View details
A Scalable Framework for Evaluating Health Language Models
Neil Mallinar
Tony Faranesh
Brent Winslow
Nova Hammerquist
Ben Graef
Cathy Speed
Mark Malhotra
Shwetak Patel
Xavi Prieto
Daniel McDuff
Ahmed Metwally
(2025)
Preview abstract
Large language models (LLMs) have emerged as powerful tools for analyzing complex datasets. Recent studies demonstrate their potential to generate useful, personalized responses when provided with patient-specific health information that encompasses lifestyle, biomarkers, and context. As LLM-driven health applications are increasingly adopted, rigorous and efficient one-sided evaluation methodologies are crucial to ensure response quality across multiple dimensions, including accuracy, personalization and safety. Current evaluation practices for open-ended text responses heavily rely on human experts. This approach introduces human factors and is often cost-prohibitive, labor-intensive, and hinders scalability, especially in complex domains like healthcare where response assessment necessitates domain expertise and considers multifaceted patient data. In this work, we introduce Adaptive Precise Boolean rubrics: an evaluation framework that streamlines human and automated evaluation of open-ended questions by identifying gaps in model responses using a minimal set of targeted rubrics questions. Our approach is based on recent work in more general evaluation settings that contrasts a smaller set of complex evaluation targets with a larger set of more precise, granular targets answerable with simple boolean responses. We validate this approach in metabolic health, a domain encompassing diabetes, cardiovascular disease, and obesity. Our results demonstrate that Adaptive Precise Boolean rubrics yield higher inter-rater agreement among expert and non-expert human evaluators, and in automated assessments, compared to traditional Likert scales, while requiring approximately half the evaluation time of Likert-based methods. This enhanced efficiency, particularly in automated evaluation and non-expert contributions, paves the way for more extensive and cost-effective evaluation of LLMs in health.
View details
Preview abstract
Julia's strength in mathematical computation and high performance makes it a popular choice across scientific fields, mostly due to its focus on mathematics in a broad sense and execution performance. It is a language of choice to implement new numerical algorithms, but it really shines in modelling for optimisation thanks to JuMP.jl and MathOptInterface.jl.
These libraries are, first and foremost, made for mathematical optimisation (linear, mixed-integer, conic, etc.), yet they are now generic enough to support more paradigms, such as constraint programming. This talk will introduce the basic principles behind the current implementation of JuMP.jl and explain why and how they are very good matches for modelling using constraint programming… and solving using any kind of mixed-integer-programming solver.
Constraint-programming solvers can also be implemented using linear programming, in a great collaboration between discrete and continuous optimisation. This talk will briefly explain the connection and its implementation in Google’s CP-SAT, a leading, award-winning constraint solver that uses linear programs in its solving process — a solver that will soon be available in Julia too.
View details
Beyond Digital Literacy: Building Youth Digital Resilience Through Existing “Information Sensibility” Practices
Mia Hassoun
Ian Beacock
Todd Carmody
Patrick Gage Kelley
Beth Goldberg
Devika Kumar
Laura Murray
Rebekah Park
Behzad Sarmadi
Social Sciences Journal, 14(4) (2025)
Preview abstract
Youth media consumption and disordered eating practices have historically been subjects of moral panics, often resulting in protective, deficit-based interventions like content removal. We argue for interventions which instead equip youth to evaluate and manage risks in their online environments, building upon their existing “information sensibility” practices. Drawing upon ethnographic research and intervention testing with 77 participants in the US and India, we analyze how youth (aged 13–26), including those with diverse political perspectives and those recovering from disordered eating (DE), engage with online news and health information. Participants generally algorithmically encountered (rather than searched for) information online, and their engagement was shaped more by social motivations—like belonging—than truth seeking. Participants interpreted online information collaboratively, relying on social cues and peer validation within their online communities. They demonstrated preference for personal testimonies and relatable sources, particularly those with similar social identities. We propose resilience-building interventions that build upon these youth online information practices by: (1) leveraging peer networks, promoting critical information engagement through collaborative learning and peer-to-peer support within online communities; (2) developing social media sensibility, equipping youth to critically evaluate information sources in situ; (3) providing pathways offline, connecting youth to desired in-person communities; and (4) encouraging probabilistic thinking.
View details
Model Swarms: Collaborative Search of Adapted LLM Experts via Swarm Intelligence
Shangbin Feng
Yike Wang
Nathalie Rauschmayr
Yejin Choi
Yulia Tsvetkov
ICML 2025
Preview abstract
We propose Model Swarms, a collaborative search algorithm to adapt LLM experts via swarm intelligence. Specifically, Model Swarms starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and search for adapted models that optimize the utility function. Compared to existing model composition approaches, Model Swarms offers modularity, works in low-data regimes, and doesn't need assumptions about existing experts and how they should be composed. Extensive experiments demonstrate that Model Swarms could flexibly adapt LLM experts to a single dataset, multi-dataset domains, reward models, as well as diverse human preferences. Further analysis reveals that LLM experts discover previously unseen capabilities in the search process and that Model Swarms enable the weak-to-strong transition of experts through the collaborative search process.
View details
SSDTrain: Faster Large Language Model Training Using SSD-Based Activation Offloading
Kun Wu
Jeongmin Brian Park
Mert Hidayetoğlu
Vikram Sharma Mailthody
Sitao Huang
Steven Lumetta
Wen-mei Hwu
Design Automation Conference (DAC) (2025)
Preview abstract
The scaling up of Large Language Models (LLMs) demands more memory than current GPUs can provide, hindering the training process. To address this challenge, we propose SSDTrain to efficiently offload activations, the intermediate tensors produced during LLM training, to SSDs. This approach reduces GPU memory usage without impacting performance by adaptively overlapping data transfers with computation. SSDTrain is compatible with popular deep learning frameworks like PyTorch, Megatron, and DeepSpeed, and it employs techniques such as tensor deduplication, forwarding, and adaptive offloading to further enhance efficiency. We conduct extensive experiments on Llama, BERT, and T5. Results demonstrate that SSDTrain effectively reduces 45% of the activation peak memory usage. It can perfectly overlap the IO with the computation without introducing performance penalty. SSDTrain can achieve a performance boost of up to 31% compared to the conventional training strategy using the same GPU systems.
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
