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 10456 publications
Preview abstract
Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks. In particular, improvements in reasoning abilities and the expansion of context windows have opened new avenues for leveraging these powerful models.
NL2SQL is challenging in that the natural language question is inherently ambiguous, while the SQL generation requires a precise understanding of complex data schema and semantics. One approach to this semantic ambiguous problem is to provide more and sufficient contextual information.
In this work, we explore the performance and the latency trade-offs of the extended context window (a.k.a., long context) offered by Google's state-of-the-art LLM (\textit{gemini-1.5-pro}).
We study the impact of various contextual information, including column example values, question and SQL query pairs, user-provided hints, SQL documentation, and schema. To the best of our knowledge, this is the first work to study how the extended context window and extra contextual information can help NL2SQL generation with respect to both accuracy and latency cost.
We show that long context LLMs are robust and do not get lost in the extended contextual information. Additionally, our long-context NL2SQL pipeline based on Google's \textit{gemini-pro-1.5} achieve a strong performance with 67.41\% on BIRD benchmark (dev) without finetuning and expensive self-consistency based techniques.
View details
Generative AI for medical education: Insights from a case study with medical students and an AI tutor for clinical reasoning
Amy Wang
Roma Ruparel
Paul Jhun
Julie Anne Seguin
Patricia Strachan
Renee Wong
2025
Preview abstract
Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), have demonstrated significant potential in clinical reasoning skills such as history-taking and differential diagnosis generation—critical aspects of medical education. This work explores how LLMs can augment medical curricula through interactive learning. We conducted a participatory design process with medical students, residents and medical education experts to co-create an AI-powered tutor prototype for clinical reasoning. As part of the co-design process, we conducted a qualitative user study, investigating learning needs and practices via interviews, and conducting concept evaluations through interactions with the prototype. Findings highlight the challenges learners face in transitioning from theoretical knowledge to practical application, and how an AI tutor can provide personalized practice and feedback. We conclude with design considerations, emphasizing the importance of context-specific knowledge and emulating positive preceptor traits, to guide the development of AI tools for medical education.
View details
Fast electronic structure quantum simulation by spectrum amplification
Guang Hao Low
Robbie King
Dominic Berry
Qiushi Han
Albert Eugene DePrince III
Alec White
Rolando Somma
arXiv:2502.15882 (2025)
Preview abstract
The most advanced techniques using fault-tolerant quantum computers to estimate the ground-state energy of a chemical Hamiltonian involve compression of the Coulomb operator through tensor factorizations, enabling efficient block-encodings of the Hamiltonian. A natural challenge of these methods is the degree to which block-encoding costs can be reduced. We address this challenge through the technique of spectrum amplification, which magnifies the spectrum of the low-energy states of Hamiltonians that can be expressed as sums of squares. Spectrum amplification enables estimating ground-state energies with significantly improved cost scaling in the block encoding normalization factor $\Lambda$ to just $\sqrt{2\Lambda E_{\text{gap}}}$, where $E_{\text{gap}} \ll \Lambda$ is the lowest energy of the sum-of-squares Hamiltonian. To achieve this, we show that sum-of-squares representations of the electronic structure Hamiltonian are efficiently computable by a family of classical simulation techniques that approximate the ground-state energy from below. In order to further optimize, we also develop a novel factorization that provides a trade-off between the two leading Coulomb integral factorization schemes-- namely, double factorization and tensor hypercontraction-- that when combined with spectrum amplification yields a factor of 4 to 195 speedup over the state of the art in ground-state energy estimation for models of Iron-Sulfur complexes and a CO$_{2}$-fixation catalyst.
View details
Score-based Causal Representation Learning: Linear and General Transformations
Burak Varici
Emre Acarturk
Abhishek Kumar
Ali Tajer
Journal of Machine Learning Research (JMLR) 2025 (2025)
Preview abstract
This paper addresses intervention-based causal representation learning (CRL) under a
general nonparametric latent causal model and an unknown transformation that maps the
latent variables to the observed variables. Linear and general transformations are investigated. The paper addresses both the identifiability and achievability aspects. Identifiability
refers to determining algorithm-agnostic conditions that ensure the recovery of the true
latent causal variables and the underlying latent causal graph. Achievability refers to the algorithmic aspects and addresses designing algorithms that achieve identifiability guarantees.
By drawing novel connections between score functions (i.e., the gradients of the logarithm of
density functions) and CRL, this paper designs a score-based class of algorithms that ensures
both identifiability and achievability. First, the paper focuses on linear transformations and
shows that one stochastic hard intervention per node suffices to guarantee identifiability. It
also provides partial identifiability guarantees for soft interventions, including identifiability
up to mixing with parents for general causal models and perfect recovery of the latent graph
for sufficiently nonlinear causal models. Secondly, it focuses on general transformations
and demonstrates that two stochastic hard interventions per node are sufficient for identifiability. This is achieved by defining a differentiable loss function whose global optima
ensure identifiability for general CRL. Notably, one does not need to know which pair of
interventional environments has the same node intervened. Finally, the theoretical results
are empirically validated via experiments on structured synthetic data and image data.
View details
Preview abstract
Browser fingerprinting enables persistent cross-site user tracking via subtle techniques that often evade conventional defenses or cause website breakage when script-level blocking countermeasures are applied. Addressing these challenges requires detection methods offering both function-level precision to minimize breakage and inherent robustness against code obfuscation and URL manipulation.
We introduce ByteDefender, the first system leveraging V8 engine bytecode to detect fingerprinting operations specifically at the JavaScript function level. A Transformer-based classifier, trained offline on bytecode sequences, accurately identifies functions exhibiting fingerprinting behavior. We develop and evaluate lightweight signatures derived from this model to enable low-overhead, on-device matching against function bytecode during compilation but prior to execution, which only adds a 4% (average) latency to the page load time. This mechanism facilitates targeted, real-time prevention of fingerprinting function execution, thereby preserving legitimate script functionality. Operating directly on bytecode ensures inherent resilience against common code obfuscation and URL-based evasion. Our evaluation on the top 100k websites demonstrates high detection accuracy at both function- and script-level, with substantial improvements over state-of-the-art AST-based methods, particularly in robustness against obfuscation. ByteDefender offers a practical framework for effective, precise, and robust fingerprinting mitigation.
View details
Preview abstract
This tutorial examines the progress and scaling limitations of IM-DD based optical technologies and explores how datacenter use cases optimized coherent technology, including a newly proposed polarization-folding, time-diversity approach and a novel single-sideband coherent detection technology—can address some of these challenges
View details
Neural Pathways to Program Success: Hopfield Networks for PERT Analysis
Proceedings of Technology and Engineering Management Society Conference (TEMSCON Global), IEEE (2025)
Preview abstract
Project and task scheduling under uncertainty remains a fundamental challenge in program and project management, where accurate estimation of task durations and dependencies is critical for delivering complex, multi project systems. The Program Evaluation and Review Technique provides a probabilistic framework to model task variability and critical paths. In this paper, the author presents a novel formulation of PERT scheduling as an energy minimization problem within a Hopfield neural network architecture. By mapping task start times and precedence constraints into a neural computation framework, the networks inherent optimization dynamics is exploited to approximate globally consistent schedules. The author addresses key theoretical issues related to energy function differentiability, constraint encoding, and convergence, and extends the Hopfield model for structured precedence graphs. Numerical simulations on synthetic project networks comprising up to 1000 tasks demonstrate the viability of this approach, achieving near optimal makespans with minimal constraint violations. The findings suggest that neural optimization models offer a promising direction for scalable and adaptive project tasks scheduling under uncertainty in areas such as the agentic AI workflows, microservice based applications that the modern AI systems are being built upon.
View details
Preview abstract
We discuss the challenges posed by growing machine learning workloads on
datacenter networks and present how Google’s Jupiter network fabrics effectively support
diverse traffic.
View details
Preview abstract
This paper presents SYMBIOSIS, an AI-powered framework to make Systems Thinking accessible for addressing societal challenges and unlock paths for leveraging systems thinking framework to improve AI systems. The platform establishes a centralized, open-source repository of systems thinking/system dynamics models categorized by Sustainable Development Goals (SDGs) and societal topics using topic modeling and classification techniques. Systems Thinking resources, though critical for articulating causal theories in complex problem spaces, are often locked behind specialized tools and intricate notations, creating high barriers to entry. To address this, we developed a generative co-pilot that translates complex systems representations - such as causal loops and stock-flow diagrams - into natural language (and vice-versa), allowing users to explore and build models without extensive technical training.
Rooted in community-based system dynamics (CBSD) and informed by community-driven insights on societal context, we aim to bridge the problem understanding chasm. This gap, driven by epistemic uncertainty, often limits ML developers who lack the community-specific knowledge essential for problem understanding and formulation, often leading to misaligned causal theories and reduced intervention effectiveness. Recent research identifies causal and abductive reasoning as crucial frontiers for AI, and Systems Thinking provides a naturally compatible framework for both. By making Systems Thinking frameworks more accessible and user-friendly, we aim to serve as a foundational step to unlock future research into Responsible and society-centered AI that better integrates societal context leveraging systems thinking framework and models. Our work underscores the need for ongoing research into AI's capacity essential system dynamics such as feedback processes and time delays, paving the way for more socially attuned, effective AI systems.
View details
AfriMed-QA: A Pan-African Multi-Specialty Medical Question-Answering Benchmark Dataset
Tobi Olatunji
Abraham Toluwase Owodunni
Charles Nimo
Jennifer Orisakwe
Henok Biadglign Ademtew
Chris Fourie
Foutse Yuehgoh
Stephen Moore
Mardhiyah Sanni
Emmanuel Ayodele
Timothy Faniran
Bonaventure F. P. Dossou
Fola Omofoye
Wendy Kinara
Tassallah Abdullahi
Michael Best
2025
Preview abstract
Recent advancements in large language model (LLM) performance on medical multiple-choice question (MCQ) benchmarks have stimulated significant interest from patients and healthcare providers globally. Particularly in low- and middle-income countries (LMICs) facing acute physician shortages and lack of specialists, LLMs offer a potentially scalable pathway to enhance healthcare access and reduce costs. However, LLM training data is sourced from predominantly Western text, existing benchmarks are predominantly Western-centric, limited to MCQs, and focused on a narrow range of clinical specialties, raising concerns about their applicability in the Global South, particularly across Africa where localized medical knowledge and linguistic diversity are often underrepresented. In this work, we introduce AfriMed-QA, the first large-scale multi-specialty Pan-African medical Question-Answer (QA) dataset designed to evaluate and develop equitable and effective LLMs for African healthcare. It contains 3,000 multiple-choice professional medical exam questions with answers and rationale, 1,500 short answer questions (SAQ) with long-from answers, and 5,500 consumer queries, sourced from over 60 medical schools across 15 countries, covering 32 medical specialties. We further rigorously evaluate multiple open, closed, general, and biomedical LLMs across multiple axes including accuracy, consistency, factuality, bias, potential for harm, local geographic relevance, medical reasoning, and recall. We believe this dataset provides a valuable resource for practical application of large language models in African healthcare and enhances the geographical diversity of health-LLM benchmark datasets.
View details
Score-based Causal Representation Learning: Linear and General Transformations
Abhishek Kumar
Emre Acarturk
Ali Tajer
Burak Varici
Journal of Machine Learning Research (JMLR) 2025 (2025)
Preview abstract
This paper addresses intervention-based causal representation learning (CRL) under a general
nonparametric latent causal model and an unknown transformation that maps the latent variables to the observed variables. Linear and general transformations are investigated. The paper addresses both the identifiability and achievability aspects. Identifiability refers to determining algorithm-agnostic conditions that ensure recovering the true latent causal variables and the latent causal graph underlying them. Achievability refers to the algorithmic aspects and addresses designing algorithms that achieve identifiability guarantees. By drawing novel connections between score functions (i.e., the gradients of the logarithm of density functions) and CRL, this paper designs a score-based class of algorithms that ensures both identifiability and achievability. First, the paper focuses on linear transformations and shows that one stochastic hard intervention per node suffices to guarantee identifiability. It also provides partial identifiability guarantees for soft interventions, including identifiability up to ancestors for general causal models and perfect latent graph recovery for sufficiently non-linear causal models. Secondly, it focuses on general transformations and shows that two stochastic hard interventions per node suffice for identifiability. Notably, one does not need to know which pair of interventional environments have the same node intervened.
View details
Databases in the Era of Memory-Centric Computing
Yannis Chronis
Anastasia Ailamaki
Lawrence Benson
Helena Caminal
Jana Gičeva
Eric Seldar
Lisa Wu Wills
2025
Preview abstract
The increasing disparity between processor core counts and memory bandwidth, coupled with the rising cost and underutilization of memory, introduces a performance and cost Memory Wall and presents a significant challenge to the scalability of database systems. We argue that current processor-centric designs are unsustainable, and we advocate for a shift towards memory-centric computing, where disaggregated memory pools enable cost-effective scaling and robust performance. Database systems are uniquely positioned to leverage memory-centric systems because of their intrinsic data-centric nature. We demonstrate how memory-centric database operations can be realized with current hardware, paving the way for more efficient and scalable data management in the cloud.
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
TOKENFORMER: Rethinking Transformers Scaling with Tokenized Model Parameters
Haiyang Wang
Fan Yue
Jan Eric Lenssen
Liwei Wang
Bernt Schiele
2025
Preview abstract
Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises primarily from their dependence on fixed parameters within linear projections, especially when architectural modifications (e.g., channel dimensions) are introduced. Each scaling iteration typically requires retraining the entire model from the beginning, leading to suboptimal utilization of computational resources. To overcome this limitation, we introduce TokenFormer, a naturally scalable architecture that leverages the attention mechanism exclusively for computations among input tokens and interactions between input tokens and model parameters, thereby enhancing architectural flexibility. By treating model parameters as tokens, we replace all the linear projections in Transformer with our token-parameter attention layer, where input tokens act as queries and model parameters as keys and values. This innovative approach allows for progressive and efficient scaling without necessitating retraining from scratch. Our model scales from 124 million to 1.4 billion parameters by incrementally adding new key-value parameters, achieving performance comparable to models trained from scratch while greatly reducing training costs. Code and models will be publicly available.
View details
DORA Impact of Generative AI in Software Development
Derek DeBellis
Daniella Villalba
Nathen Harvey
DORA, Google (2025)
Preview abstract
Generative AI is transforming how software is built, offering unprecedented opportunities and raising new challenges. Based on extensive research and developer interviews, this DORA report provides a nuanced understanding of AI's impact on individuals, teams, and organizations.
View details
