Jump to Content

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.

people standing in front of a screen with images and a chipboard

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.

results

Year

Team

Research Area

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
1 - 15 of 10795 publications
    FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
    Victor May
    Diganta Misra
    Yanqi Luo
    Anjali Sridhar
    Justine Gehring
    Silvio Soares Ribeiro Junior
    2026
    Preview abstract AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent of powerful large language models (LLMs), AI-driven agentic frameworks offer a promising alternative—but their effectiveness remains underexplored. In this paper, we introduce FreshBrew, a novel benchmark for evaluating AI-based agentic frameworks on project-level Java migrations. We benchmark several such frameworks, powered by state-of-the-art LLMs, and compare their performance against established rule-based tools. Our evaluation of AI agents on this benchmark of 228 repositories shows that the top-performing model, Gemini 2.5 Flash, can successfully migrate 56.5% of projects to JDK 17. Our empirical analysis reveals novel insights into the critical strengths and limitations of current agentic approaches, offering actionable insights into their real-world applicability. By releasing FreshBrew publicly upon acceptance, we aim to facilitate rigorous, reproducible evaluation and catalyze progress in AI-driven codebase modernization. View details
    Productionizing Quantum Mass Production
    Bill Huggins
    Tanuj Khattar
    Nathan Wiebe
    arXiv for now (2026) (to appear)
    Preview abstract For many practical applications of quantum computing, the slowest and most costly steps involve coherently accessing classical data. We help address this challenge by applying mass production techniques, which can sometimes allow us to perform operations many times in parallel for a cost that is comparable to a single execution[1-3]. We combine existing mass-production results with modern approaches for loading classical data using ``quantum read-only memory.'' We show that quantum mass production techniques offer no benefit when we consider a cost model that focuses purely on the number of non-Clifford gates. However, analyzing the constant factors in a more nuanced cost model, we find that it may be possible to obtain a reduction in cost of an order or magnitude or more for a variety reasonably-sized fault-tolerant quantum algorithms. We present several applications of quantum mass-production techniques beyond naive parallelization, including a strategy for reducing the cost of serial calls to the same data loading step. View details
    Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information
    Dirk Bergemann
    Marek Bojko
    Paul Duetting
    Renato Paes Leme
    Haifeng Xu
    Song Zuo
    EC '25: Proceedings of the 26th ACM Conference on Economics and Computation (2025), pp. 507
    Preview abstract We study mechanism design when agents have private preferences and private information about a common payoff-relevant state. We show that standard message-driven mechanisms cannot implement socially efficient allocations when agents have multidimensional types, even under favorable conditions. To overcome this limitation, we propose data-driven mechanisms that leverage additional post-allocation information, modeled as an estimator of the payoff-relevant state. Our data-driven mechanisms extend the classic Vickrey-Clarke-Groves class. We show that they achieve exact implementation in posterior equilibrium when the state is either fully revealed or the utility is affine in an unbiased estimator. We also show that they achieve approximate implementation with a consistent estimator, converging to exact implementation as the estimator converges, and present bounds on the convergence rate. We demonstrate applications to digital advertising auctions and large language model (LLM)-based mechanisms, where user engagement naturally reveals relevant information. View details
    Sequentially Auditing Differential Privacy
    Tomas Gonzalez Lara
    Mateo Dulce
    Aaditya Ramdas
    Monica Ribero
    Annual Conference on Neural Information Processing Systems (NeurIPS) (2025)
    Preview abstract We propose a practical sequential test for auditing differential privacy guarantees of black-box mechanisms. The test processes streams of mechanisms' outputs providing anytime valid inference while controlling Type I error, overcoming the fixed sample size limitation of previous batch auditing methods. Experiments show this test detects violations with sample sizes that are orders of magnitude smaller than existing methods, across diverse realistic mechanisms. Notably, it identifies DP-SGD privacy violations in under one training run, unlike prior methods needing full model training. View details
    Streaming Attention Approximation via Discrepancy Theory
    Michael Kapralov
    Insu Han
    Ekaterina Kochetkova
    Kshiteej Sheth
    Amir Zandieh
    2025
    Preview abstract Large language models (LLMs) have achieved impressive success, but their high memory requirements present challenges for long-context token generation. In this paper we study the streaming complexity of attention approximation, a key computational primitive underlying token generation. Our main contribution is BalanceKV, a streaming algorithm for ϵ-approximating attention computations based on geometric process for selecting a balanced collection of Key and Value tokens as per Banaszczyk's vector balancing theory. We complement our algorithm with space lower bounds for streaming attention computation. Besides strong theoretical guarantees, BalanceKV exhibits empirically validated performance improvements over existing methods, both for attention approximation and end-to-end performance on various long context benchmarks. View details
    Day-of-the-week Awareness in Time of Day Breakpoints for Traffic Light Plans
    Ori Rottenstreich
    Eliav Buchnik
    Shai Ferster
    Tom Kalvari
    Ron Tsibulsky
    Danny Veikherman
    Avishai Zagoury
    Jack Haddad
    Dotan Emanuel
    Avinatan Hassidim
    2025
    Preview abstract Time-of-day breakpoints (TODs) refer to the times over the day in which the plan of a traffic light is changed. Traditionally, TODs are selected jointly for all weekdays (Monday-Friday), typically with additional TODs dedicated to weekends. In this paper, we present an alternative approach motivated by traffic characteristics that can differ among the weekdays Monday-Friday and consider TODs which are day-of-the-week aware. The traffic-aware approach studies similarities among days and computes TODs that can be shared among days with similar characteristics but can also have other forms for weekdays with unique characteristics. Based on traffic properties derived from anonymized trajectories, we apply the new methodology to compute time-of-day breakpoints that are day-of-the-week aware in the city of Rio de Janeiro, Brazil and estimate the impact of the new methodology. View details
    Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-Answering
    Eviatar Nachshoni
    Arie Cattan
    Shmuel Amar
    Ori Shapira
    Ido Dagan
    2025
    Preview abstract Large Language Models (LLMs) have demonstrated strong performance in question answering (QA) tasks. However, Multi-Answer Question Answering (MAQA), where a question may have several valid answers, remains challenging. Traditional QA settings often assume consistency across evidences, but MAQA can involve conflicting answers. Constructing datasets that reflect such conflicts is costly and labor-intensive, while existing benchmarks often rely on synthetic data, restrict the task to yes/no questions, or apply unverified automated annotation. To advance research in this area, we extend the conflict-aware MAQA setting to require models not only to identify all valid answers, but also to detect specific conflicting answer pairs, if any. To support this task, we introduce a novel cost-effective methodology for leveraging fact-checking datasets to construct NATCONFQA, a new benchmark for realistic, conflict-aware MAQA, enriched with detailed conflict labels, for all answer pairs. We evaluate eight high-end LLMs on NATCONFQA, revealing their fragility in handling various types of conflicts and the flawed strategies they employ to resolve them. View details
    The Discrete Adiabatic Quantum Linear System Solver has Lower Constant factors than the Randomized Adiabatic Solver
    Pedro C. S. Costa
    Dong An
    Ryan Babbush
    Dominic Berry
    Quantum, 9 (2025), pp. 1887
    Preview abstract The solution of linear systems of equations is the basis of many other quantum algorithms, and recent results provided an algorithm with optimal scaling in both the condition number κ and the allowable error ϵ [PRX Quantum 3, 0403003 (2022)]. That work was based on the discrete adiabatic theorem, and worked out an explicit constant factor for an upper bound on the complexity. Here we show via numerical testing on random matrices that the constant factor is in practice about 1,200 times smaller than the upper bound found numerically in the previous results. That means that this approach is far more efficient than might naively be expected from the upper bound. In particular, it is over an order of magnitude more efficient than using a randomized approach from [arXiv:2305.11352] that claimed to be more efficient. View details
    Emerging AI Trends for Sustainable Data Centers
    Venkat Sharma Gaddala
    Vandana Kollati
    International Journal of Management, IT & Engineering (2025)
    Preview abstract As the demand for data and digital services continues to escalate, data centers are evolving into key players in the global energy consumption landscape. The necessity for sustainability and energy efficiency in these facilities has led to the integration of Artificial Intelligence (AI) technologies. This paper explores emerging AI trends that are shaping sustainable data centers, focusing on optimization, predictive analytics, and machine learning applications, along with their implications for operational efficiency and environmental impact. The rapid growth of artificial intelligence (AI) has significantly impacted data center operations, driving the need for sustainable practices. Emerging trends such as AI-driven energy optimization, renewable energy integration, and advanced cooling technologies are reshaping the industry. These innovations aim to reduce energy consumption, minimize carbon footprints, and enhance operational efficiency. By leveraging AI, data centers can predict maintenance needs, optimize energy usage, and adapt to real-time demands. This paper explores the intersection of AI and sustainability, highlighting how these advancements contribute to a more eco-friendly and efficient future for data centers. View details
    Online Bidding under RoS Constraints without Knowing the Value
    Sushant Vijayan
    Zhe Feng
    Swati Padmanabhan
    Karthikeyan Shanmugam
    Arun Suggala
    Di Wang
    The Web Conference (2025)
    Preview abstract We consider the problem of auto-bidding in online advertising from the perspective of a single advertiser. The goal of the advertiser is to maximize their value under the Return-on-Spend (RoS) constraint, with performance measured in terms of \emph{regret} against the optimal offline solution that knows all queries a priori. Importantly, the value of the item is \textit{unknown} to the bidder ahead of time. The goal of the bidder is to quickly identify the optimal bid, while simultaneously satisfying budget and RoS constraints. Using a simple UCB-style algorithm, we provide the first result which achieves optimal regret and constraint violation for this problem. View details
    The Impact of New Information Disclosure on Firm's Information Asymmetry and Liquidity
    Aida Davani
    Sahand Davani
    2025
    Preview abstract We study the effect of a firm's new information disclosure on the information asymmetry between its informed and uninformed investors and its liquidity. To do this, we employ advanced natural language processing (NLP) methods to introduce a novel measure of firms' 10-K filing predictability that quantifies the amount of new information in these reports. Our findings show that more new information is associated with higher bid-ask spreads and lower trading volumes, indicating increased information asymmetry and reduced liquidity, respectively. Notably, institutional ownership moderates these effects, suggesting that sophisticated investors can mitigate the adverse consequences of disclosure unpredictability. An event study analysis further reveals that more new information triggers increased trading activity and abnormal returns immediately after disclosure, though these effects are short-lived. View details
    V𝜖rity: Verifiable Local Differential Privacy
    Mariana Raykova
    Amrita Roy Chowdhury
    Baiyu Li
    Adria Gascon
    James Bell-Clark
    2025
    Preview abstract Local differential privacy (LDP) enables individuals to report sensitive data while preserving privacy. Unfortunately, LDP mechanisms are vulnerable to poisoning attacks, where adversaries controlling a fraction of the reporting users can significantly distort the aggregate output–much more so than in a non-private solution where the inputs are reported directly. In this paper, we present two novel solutions that prevent poisoning attacks under LDP while preserving its privacy guarantees. Our first solution, Vϵrity-Auth, addresses scenarios where the users report inputs with a ground truth available to a third party. The second solution, Vϵrity, tackles the more challenging case in which the users locally generate their input and there is no ground truth which can be used to bootstrap verifiable randomness generation. View details
    Probing non-equilibrium topological order on a quantum processor
    Melissa Will
    Tyler Cochran
    Eliott Rosenberg
    Bernhard Jobst
    Norhan Eassa
    Pedram Roushan
    Michael Knap
    Adam Gammon-Smith
    Frank Pollmann
    Nature, 645 (2025), 348–353
    Preview abstract Out-of-equilibrium phases in many-body systems constitute a new paradigm in quantum matter—they exhibit dynamical properties that may otherwise be forbidden by equilibrium thermodynamics. Among these non-equilibrium phases are periodically driven (Floquet) systems, which are generically difficult to simulate classically because of their high entanglement. Here we realize a Floquet topologically ordered state on an array of superconducting qubits. We image the characteristic dynamics of its chiral edge modes and characterize its emergent anyonic excitations. Devising an interferometric algorithm allows us to introduce and measure a bulk topological invariant to probe the dynamical transmutation of anyons for system sizes up to 58 qubits. Our work demonstrates that quantum processors can provide key insights into the thus-far largely unexplored landscape of highly entangled non-equilibrium phases of matter. View details
    Mind the GAP: Geometry Aware Passthrough Mitigates Cybersickness
    Trishia Chemaly
    Mohit Goyal
    Francis Duan
    Vrushank Phadnis
    Sakar Khattar
    Bjorn Vlaskamp
    Ace Kulshrestha
    Eric Turner
    Aveek Purohit
    Greg Neiswander
    Konstantine Tsotsos
    2025
    Preview abstract Virtual Reality headsets isolate users from the real-world by restricting their perception to the virtual-world. Video See-Through (VST) headsets address this by utilizing world-facing cameras to create Augmented Reality experiences. However, directly displaying camera feeds can cause visual discomfort and cybersickness due to the inaccurate perception of scale and exaggerated motion parallax. This paper presents initial findings on the potential of geometry aware passthrough systems to mitigate cybersickness through enhanced depth perception. We introduce a promising protocol for quantitatively measuring cybersickness experienced by users in VST headsets. Using this protocol, we conduct a user study to compare direct passthrough and geometry aware passthrough systems. To the best of our knowledge, our study is the first one to reveal reduced nausea, disorientation, and total scores of cybersickness with geometry aware passthrough. It also uncovers several potential avenues to further mitigate visually-induced discomfort. View details
    Deep Researcher with Test-time Diffusion
    Rujun Han
    Yanfei Chen
    Guan Sun
    Lesly Miculicich
    Zoey CuiZhu
    Yuanjun (Sophia) Bi
    Weiming Wen
    Hui Wan
    Chunfeng Wen
    Solène Maître
    George Lee
    Vishy Tirumalashetty
    Emily Xue
    Zizhao Zhang
    Salem Haykal
    Burak Gokturk
    Tomas Pfister
    Chen-Yu Lee
    2025
    Preview abstract Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports using generic test-time scaling algorithms. Drawing inspiration from the iterative nature of human research, which involves cycles of searching, reasoning, and revision, we propose the Test-Time Diffusion Deep Researcher (TTD-DR). This novel framework conceptualizes research report generation as a diffusion process. TTD-DR initiates this process with a preliminary draft, an updatable skeleton that serves as an evolving foundation to guide the research direction. The draft is then iteratively refined through a "denoising" process, which is dynamically informed by a retrieval mechanism that incorporates external information at each step. The core process is further enhanced by a self-evolutionary algorithm applied to each component of the agentic workflow, ensuring the generation of high-quality context for the diffusion process. This draft-centric design guides the report writing process to be more timely and coherent while reducing information loss during the iterative search process. We demonstrate that our TTD-DR achieves state-of-the-art results on a wide array of benchmarks that require intensive search and multi-hop reasoning, significantly outperforming existing deep research agents. View details
    Search on Google Scholar

    Follow Lee on X/Twitter - Father, Husband, Serial builder creating AI, crypto, games & web tools. We are friends :) AI Will Come To Life!

    Check out: eBank.nz (Art Generator) | Netwrck.com (AI Tools) | Text-Generator.io (AI API) | BitBank.nz (Crypto AI) | ReadingTime (Kids Reading) | RewordGame | BigMultiplayerChess | WebFiddle | How.nz | Helix AI Assistant