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 11415 publications
Mull-Tokens: Modality-Agnostic Latent Thinking
Arijit Ray
Chengzhi Mao
Bryan A. Plummer
Kate Saenko
Ranjay Krishna
Leonidas Guibas
Vincent Chu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (Findings) (2026) (to appear)
Preview abstract
Reasoning goes beyond language; the real world requires reasoning about space, time, affordances, and much more that words alone cannot convey. Existing multimodal models exploring the potential of reasoning with images are brittle and do not scale. They rely on calling specialist tools, costly generation of images, or handcrafted reasoning data to switch between text and image thoughts. Instead, we offer a simpler alternative -- Mull-Tokens -- modality-agnostic latent tokens pre-trained to hold intermediate information in either image or text modalities to let the model think free-form towards the correct answer. We investigate best practices to train Mull-Tokens inspired by latent reasoning frameworks. We first train Mull-Tokens using supervision from interleaved text-image traces, and then fine-tune without any supervision by only using the final answers. Across four challenging spatial reasoning benchmarks involving tasks such as solving puzzles and taking different perspectives, we demonstrate that Mull-Tokens improve upon several baselines utilizing text-only reasoning or interleaved image-text reasoning, achieving a +3% average improvement and up to +16% on a puzzle solving reasoning-heavy split compared to our strongest baseline. Adding to conversations around challenges in grounding textual and visual reasoning, Mull-Tokens offers a simple solution to abstractly think in multiple modalities.
View details
An AI system to help scientists write expert-level empirical software
Eser Aygün
Anastasiya Belyaeva
Gheorghe Comanici
Hao Cui
Renee Johnston
Zahra Shamsi
David Smalling
James Thompson
Sarah Martinson
Lai Wei
Yuchen Zhou
Qian-Ze Zhu
Matthew Abraham
Erica Brand
Anna Bulanova
Jeffrey Cardille
Chris Co
Scott Ellsworth
Grace Joseph
Malcolm Kane
Ryan Krueger
Johan Kartiwa
Jackson Cui
Paul Raccuglia
Julie Wang
Kat Chou
James Manyika
Lizzie Dorfman
Shibl Mourad
Nature (2026)
Preview abstract
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments. To address this, we present Empirical Research Assistance (ERA), an AI system that creates expert-level scientific software whose goal is to maximize a quality metric. The system uses a Large Language Model (LLM) and Tree Search (TS) to systematically improve the quality metric and intelligently navigate the large space of possible solutions. ERA achieves expert-level results when it explores and integrates complex research ideas from external sources. The effectiveness of tree search is demonstrated across a diverse range of tasks. In bioinformatics, ERA discovered 40 novel methods for single-cell data analysis that outperformed the top human-developed methods on a public leaderboard. In epidemiology, ERA generated 14 models that outperformed the CDC ensemble and all other individual models for forecasting COVID-19 hospitalizations. ERA also produced expert-level software for geospatial analysis, neural activity prediction in zebrafish, and numerical solution of integrals, and a novel rule-based construction for time series forecasting. By devising and implementing novel solutions to diverse tasks, ERA represents a significant step towards accelerating scientific progress.
Keywords: Tree Search, Generative AI, Scorable Scientific Tasks, Empirical Software
View details
Preview abstract
Here’s a thought experiment. Say I wave a magic wand across a codebase and an entire class of technical debt, poof, goes away and immediately evaporates if introduced in the future. For example, maybe I make it so that dead feature flags are simply no longer a problem: they just delete themselves as soon as the engineer wills it. Or maybe large-scale migrations just migrate themselves. Maybe we magically have 100% test coverage, without an engineer lifting a finger.
What will happen to developer productivity?
Surely, developer productivity increases overall.
But will the productivity metrics that we all use as a proxy for “developer productivity” move up and to the right. Let’s explore this idea.
View details
Preview abstract
Systems for escalating interactions from automated agents to human agents can create inefficiencies, for example, by transferring unstructured transcripts. An intermediary system can employ a generative artificial intelligence synthesis engine to process the context of an automated interaction upon an escalation trigger. The engine may analyze the dialogue transcript, user metadata, and the automated agent's internal state to perform semantic abstraction, diagnose potential failure points, and infer a possible resolution. The system can then generate a structured briefing for the human agent, which could include a concise summary, a failure diagnosis, or a recommended next action presented as an interactive element. This process may facilitate a more efficient handoff and contribute to an improved escalation workflow by providing the human agent with synthesized, contextual information.
View details
Preview abstract
Source-to-source compilers may perform inefficiently by executing transpilation passes on scripts that do not contain the specific language features a pass is designed to transform, potentially leading to redundant processing. A compiler can analyze a script to generate a per-script feature map, for example, by identifying language features in its abstract syntax tree (AST). Before executing a transpilation pass, the compiler can check this map and may bypass the pass for that script if the specific feature targeted by the pass is not present. This feature map can also be dynamically updated throughout the compilation process as other passes transform the code. This method of conditional pass execution based on content-aware analysis may reduce redundant AST traversals, which could decrease overall compilation time and computational resource consumption.
View details
Preview abstract
Autonomous research agents can now produce competitive solutions and complete manuscripts, yet their papers routinely contain fabricated citations, method descriptions disconnected from the code, and scores on incorrect scales---failures invisible to evaluations that assess fluency rather than evidentiary grounding. The core problem is verifiability: no existing system maintains a traceable chain from each claim in the paper to its grounding evidence, and current evaluation protocols assess output fluency rather than evidentiary grounding. We address this with Chaine-of-Evidence (CoE), a verifiability standard requiring every claim to trace to its grounding evidence, and instantiate it in Scientist One, an end-to-end research system that maintains evidence chains natively, and CoE Audit, an evaluation protocol with four integrity checks targeting the most damaging chain failures. Auditing 60 papers from four systems, we find every baseline exhibits at least one failure: phantom citations at 4--25%, method-code alignment in at most 2/15 papers. Scientist One achieves zero phantom citations (0/830), the highest alignment rate (7/15), and competitive solver scores.
View details
What does your wearable know about the festive season?
Justin Phillips
Abram Schönfeldt
YongSuk Cho
Conor Heneghan
Robert Harle
(2026)
Preview abstract
As we reach the end of the year and people look forward to spending quality time with loved ones, here at Fitbit, we wonder what our Pixel watches and Fitbit trackers can tell us about how we are spending the festive season. We looked at the data of 11.8 million of our users all over the world between January 2022 and July 2025. Here are the key stats we wanted to share with you!
View details
Who Controls the Curriculum for AI? The Limits of Participatory Design for Educational AI
Learning Under Algorithmic Conditions, University of Minnesota Press (2026)
Preview abstract
Participatory design is a long-standing effort to shift control over technology design from technologists to users and communities impacted by technologies. For educational AI, this means involving students, families, teachers, and other stakeholders in shaping the design of AI systems. While promising, in this article, I situate the recent calls for participatory design of educational AI systems within a different historical tradition—that of contests over local control of educational curricula. I argue that approaches that attempt to steer the design and development of educational AI through participatory methods may inadvertently reproduce the history of political contestation of educational curricula, in ways that may privilege the most powerful communities, rather than those inequitably impacted. What might it look like to treat participatory AI design as a site for political contestation? How might these approaches avoid reproducing the same majoritarian tendencies that led to educational inequities in the first place?
View details
`It’s still abuse’: Community attitudes and perceptions on AI-generated image-based sexual abuse
Nicola Henry
Gemma Beard
Lisa Given
Information, Communication, & Society (2026)
Preview abstract
There are growing concerns about AI-generated image-based sexual abuse (AI-IBSA), also known as nonconsensual sexualized ′deepfakes.′ Empirical research on AI-IBSA, however, remains very limited. This study surveyed 7231 respondents across Australia, the United Kingdom, and the United States to investigate community attitudes and perceptions on AI-IBSA. Through a vignette study, we explored the relationship between public familiarity with AI-IBSA, normative concerns about consent, and context-dependent judgments that vary based on the target's identity relational status, and how the content was used. Our findings reveal strong condemnation of AI-IBSA, yet respondents demonstrated low familiarity with the technology and their views varied depending on particular contexts. AI-IBSA targeting intimate partners was viewed as more unacceptable than targeting celebrities, and content created solely for personal use was seen as less unacceptable than content intended for distribution. The study highlights the need for approaches that go beyond technical fixes and punitive measures, advocating for a multifaceted response that integrates ethical data governance, digital sexual literacy, and restorative justice approaches.
View details
Differential Sensitivity of Impedance Plethysmography and Photoplethysmography Sensors to Temperature-Induced Peripheral Vasoconstriction
Seobin Jung
Seamus Thomson
Alexandros Pantelopoulos
Lindsey Sunden
Pete Richards
Shwetak Patel
Sam Sheng
Scientific Reports (2026)
Preview abstract
Impedance plethysmography (IPG) and photoplethysmography (PPG) are non-invasive techniques for measuring blood volume changes. This study investigated the differential responses of IPG and PPG to temperature-mediated vasoconstriction induced by localized cooling. Twenty-one participants underwent control and treatment conditions, with fake or real ice cubes applied to the forearm. Blood pressure remained stable, while heart rate decreased. PPG signal amplitude significantly decreased with cooling (p_adj = 0.004), indicating sensitivity to superficial blood flow changes. In contrast, IPG signal amplitude remained stable (p_adj = 1.0). No statistically significant differences were observed in timing-derived metrics. These findings suggest IPG is less sensitive to superficial changes in blood flow than PPG, and may be more suitable for monitoring deeper blood flow. This study provides insights into the distinct sensitivities of IPG and PPG, with implications for wearable device development and cardiovascular monitoring.
View details
A Theoretical Framework for Modular Learning of Robust Generative Models
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026)
Preview abstract
Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we train Large Language Models (LLMs) modularly, combining small, domain-specific experts to match monolithic performance, and can we do so robustly for any data mixture, eliminating heuristic tuning? We present a theoretical framework for modular generative modeling where a set of pre-trained experts are combined via a gating mechanism. We define the space of normalized gating functions $\mathcal{G}_{1}$ and formulate the problem as a minimax game to find a single robust gate that minimizes divergence to the worst-case data mixture. We prove the existence of such a robust gate using Kakutani's fixed-point theorem and show that modularity acts as a strong regularizer, with generalization bounds scaling with the lightweight gate's complexity. Furthermore, we prove that this modular approach can theoretically outperform models retrained on aggregate data, with the gap characterized by the Jensen-Shannon Divergence. Finally, we introduce a scalable Stochastic Primal-Dual algorithm and a Structural Distillation method for efficient inference. Empirical results on synthetic and real-world datasets confirm that our modular architecture effectively mitigates gradient conflict and can robustly outperform monolithic baselines.
View details
Towards A Human-in-the-Loop Framework for Reliable Patch Evaluation using an LLM-as-a-Judge
Renyao Wei
Michele Tufano
José Cambronero
AI-SQE '26: Proceedings of the 1st International Workshop on AI for Software Quality Evaluation - Judgment, Metrics, Benchmarks, and Beyond, ACM (Association for Computing Machinery), New York, NY, USA (2026), pp. 19 - 28
Preview abstract
Reliable evaluation is crucial for advancing Automated Program Repair (APR), but prevailing benchmarks that rely on execution-based evaluation methods (pass@k) often fail to capture the patch quality required for real-world adoption. This creates a significant gap between automated metrics and true patch validity (valid@k), a discrepancy observed across several state-of-the-art techniques.
To develop a scalable solution for measuring valid@k, we first study the human evaluation process itself. While manual assessment can determine validity, we find it suffers from poor inter-rater reliability (Fleiss' Kappa k=0.307). Our foundational insight is that this inconsistency is largely resolved when evaluators use a shared, high-quality rubric, which significantly improves agreement.
Building on this finding, we propose an LLM-as-a-Judge framework that operationalizes rubric-guided evaluation at scale. Our method employs a human-in-the-loop workflow where an LLM first generates a candidate rubric for a given bug, which a human expert then reviews and refines into a "golden" evaluation standard. This golden rubric is then used by an LLM judge to assess the validity of candidate patches. In an evaluation on 48 bugs and 115 patches, our LLM judge demonstrates substantial agreement with the consensus of human developers. This work contributes a scalable and reliable methodology for approximating valid@k, providing a much-needed high-fidelity signal for measuring true progress in the field of automated program repair.
View details
SAC133 - SSAC Comments on Proposed Root KSK Algorithm Rollover
Wes Hardaker
Internet Corporation for Assigned Names and Numbers (ICANN), ICANN Security and Stability Advisory Committee (SSAC) Reports and Advisories (2026), pp. 9
Preview abstract
The SSAC supports the transition from RSA with SHA-256 (Algorithm 8) to ECDSA P-256
with SHA-256 (Algorithm 13) as the cryptographic algorithm for the RootKSK. The root zone
has relied on RSA-based algorithms since DNSSEC signing began in 2010. The algorithm did
not change during the first KSK rollover in 2018 or during the second rollover currently
underway and scheduled to complete in October 2026. Establishing a clear and predictable
process for algorithm transitions is essential to the long-term security of the root zone, and the
SSAC observes that the proposal addresses the Recommendation 23 of the SSR2 Review
accordingly.
The SSAC notes that the proposal builds upon the Root Zone DNSSEC Algorithm Rollover
Study published by ICANN in May 2024, which assessed resolver and authoritative server
support for alternative algorithms, analyzed rollover methodologies, and evaluated operational
risks. The SSAC finds that the proposal implements the study’s recommendations. The SSAC also notes that this proposal is consistent with the SSAC’s prior work on DNSSEC key rollover,
including SAC063, SAC073, SAC102, and SAC108.
The SSAC encourages ICANN to proceed with this rollover. Specific comments on the
proposal’s methodology, timeline, and operational readiness follow
View details
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
Preview abstract
Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most appearing infrequently. While scaling has improved average-case performance, persistent failures on low-frequency, domain-specific, cultural, and temporal knowledge remain poorly characterized. This paper develops a structured taxonomy and analysis of long-tail knowledge in large language models, synthesizing prior work across technical and sociotechnical perspectives.
We organize the literature along four complementary axes: how long-tail knowledge is defined, the mechanisms by which it is lost or distorted during training and inference, the technical interventions proposed to mitigate these failures, and the implications of these failures for fairness, accountability, transparency, and user trust. We further examine how existing evaluation practices obscure tail behavior and complicate accountability for rare but consequential failures. The paper concludes by identifying open challenges related to privacy, sustainability, and governance that constrain long-tail knowledge representation. Taken together, this paper provides a unifying conceptual framework for understanding how long-tail knowledge is defined, lost, evaluated, and manifested in deployed language model systems.
View details
