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 11645 publications
Preview abstract
Modern transformers have been scaled up in size, data, training-time compute, and more recently test-time compute based on Chain-of-Thought (CoT), but the consequences of trading off these parameters are unknown. We construct explicit tradeoffs between two of these aspects: the number of layers in a transformer and the number of CoT tokens. Our first result is general: with mild assumptions and a single-token prompt, for any integer k, a transformer using soft attention and SwiGLU MLP layers with L layers and n CoT tokens can be converted to a transformer with at most ckL layers and ⌈n/k⌉ CoT tokens, and vice versa, although with an increase to the size of other parameters. We then a multi-token prompt path following task, finding that additional preprocessing from the multi-token prompt changes the depth-CoT relationship in this case. We construct an attention-only network with L layers and 2^(L−2) heads that can traverse 2^(L−1) − 1 edges along a path with a single CoT token, demonstrating at least an exponential relationship between increases in depth and reductions in the number of CoT tokens needed to traverse the entire path. This relationship for the path following task holds empirically as well, as demonstrated by training networks with up to 5 layers, with the tradeoff between depth and the maximum number of edge traversals in a single CoT token exactly matching our theoretical constructions.
View details
A 3D Scene Graphs Survey: Open Challenges and Future Directions
Dennis Rotondi
Francesco Argenziano
Sebastian Koch
Nathan Hughes
Martin Büchner
Johanna Wald
Lukas Schmid
Daniele Nardi
Abhinav Valada
Liam Paul
Luca Carlone
Kai Arras
Annual Review of Control, Robotics, and Autonomous Systems (ARCRAS), 10 (2027) (to appear)
Preview abstract
3D Scene Graphs (3DSGs) have emerged as a powerful representation for spatial AI by combining geometric grounding with semantic and relational abstractions of the environment. Their expressiveness has made them relevant to a broad range of problems in robotics and computer vision, including mapping, task and motion planning, scene understanding, and many others. However, the field remains fragmented: different communities adopt distinct formulations, construction pipelines, and evaluation protocols, making it difficult to compare methods, identify common assumptions, and assess remaining challenges for robust real- world deployment. This survey provides a unified and critical review of 3DSGs, with particular emphasis on open challenges and future directions. We first formalize 3DSGs under a common definition and analyze the principal modeling choices that characterize existing formulations, including node and edge attributes, hierarchical structure, dynamic scene representations, and affordance-aware extensions. We then review how 3DSGs are constructed from raw sensory observations, covering both learning-oriented and construction-oriented systems. Finally, we examine downstream applications and evaluation strategies, from intrinsic graph quality to task-level performance. To support the community, we also provide a dedicated website that organizes and extends the surveyed works.
View details
When Android Apps Request Location with a Reason: A Developer Study and User Behavior Experiment
May Smith
Aman Jain
Proceedings on Privacy Enhancing Technologies (2027)
Preview abstract
Recent reports have highlighted how mobile apps share user location data with third parties, risking user privacy and platform trust. Although location data is highly sensitive, when users grant apps location access, they may not know the full extent to which it is used. We study how requiring Android apps to show a reason for location access could impact developers, users, and the platform.
We surveyed 323 Android app developers and found most supported such a requirement. The majority said it would have a positive impact on user privacy, trust for apps, and trust for Android, where impact on user trust for Android correlated most strongly with support. Many developers also said the intervention would increase the number of users granting location access. Yet their open-ended comments also revealed consistent concerns, such as apps providing dishonest reasons and platform verification.
To study the impact on user behavior, we conducted a randomized controlled experiment with 2579 US Android users. We tested how users' decisions to grant location access were impacted by app type, whether reasons were included in the requests, and the content of the reasons, including monetization. We did not find the reasons impacted users' decisions; decisions were instead driven by app type and demographics. Yet we did find the reasons could have a positive impact on user perception for the platform when the reasons did not include using data for ads. Our findings provide insights into developers' willingness to implement privacy-enhancing changes, and expose limits to improving user privacy by simply adding information to user interfaces.
View details
Approaching the Privacy-Enhancing Technologies Adoption from a Requirements Engineering Perspective
Oleksandr Kosenkov
Danica Vranjanin
Abhinava Singh
Vadym Honcharenko
Volodymyr Spirin
2026
Preview abstract
In recent decades, Privacy Enhancing Technologies (PETs) have been gaining attention as a means to fulfill regulatory and user privacy requirements when processing personal data in software systems. Despite broad attention in research, support by regulators, contributions and adoption by large technological companies (like Google or Microsoft), and interest from software developers, adoption of PETs in practice is still challenging and lagging. For many years, existing research points to the same typical challenges to the adoption of PETs, such as complexity or absence of training; however, these challenges remain unresolved in practice despite the recent efforts.
In this industrial challenge paper, we take a deeper, practical requirements engineering-driven perspective on the challenges to PETs adoption across different stakeholders (namely, PETs developers and integrators, and PET adopters and users) and different disciplines (engineering, law, and business).
We suggest that the adoption of PETs should be facilitated with an in-depth understanding of engineering, business, and legal challenges to PETs, such as PETs' impact on software architecture, their business impact, and contribution to compliance. We suggest that requirements engineering research can play a crucial role in better exploring and modeling such viewpoints. In practice, requirements engineering could facilitate the coordination of the involved viewpoints to enable the adoption of existing and the development of new PETs.
View details
MAGE: Modality-Agnostic Music Generation and Editing
Muhammad Usama Saleem
Ravi Tejasvi
Rajeev Nongpiur
Mayur Jagdishbhai Patel
Pu Wang
2026
Preview abstract
Multimodal music creation requires models that can both generate audio from high-level cues and edit existing mixtures in a targeted manner. Yet most multimodal music systems are built for a single task and a fixed prompting interface, making their conditioning brittle when guidance is ambiguous, temporally misaligned, or partially missing. Common additive fusion or feature concatenation further weakens cross-modal grounding, often causing prompt drift and spurious musical content during generation and editing. We propose MAGE, a modality-agnostic framework that unifies multimodal music generation and mixture-grounded editing within a single continuous latent formulation. At its core, MAGE uses a Controlled Multimodal FluxFormer, a flow-based Transformer that learns controllable latent trajectories for synthesis and editing under any available subset of conditions. To improve grounding, we introduce Audio-Visual Nexus Alignment to select temporally consistent visual evidence for the audio timeline, and a cross-gated modulation mechanism that applies multiplicative control from aligned visual and textual cues to the audio latents, suppressing unsupported components rather than injecting them. Finally, we train with a dynamic modality-masking curriculum that exposes the model to text-only, visual-only, joint multimodal, and mixture-guided settings, enabling robust inference under missing modalities without training separate models. Experiments on the MUSIC benchmark show that MAGE supports effective multimodal-guided music generation and targeted editing, achieving competitive quality while offering a lightweight and flexible interface tailored to practical music workflows.
View details
Preview abstract
The need for characterizing global variability of atmospheric carbon dioxide (CO2) is quickly increasing, with a growing urgency for tracking greenhouse gasses with sufficient resolution, precision and accuracy so as to support independent verification of CO2 fluxes at local to global scales. The current generation of space-based sensors, however, can only provide sparse observations in space and/or in time, by design. While upcoming missions may address some of these challenges, most are still years away from launch. This challenge has fueled interest in the potential use of data from existing missions originally developed for other applications for inferring global greenhouse gas variability. The Advanced Baseline Imager (ABI) onboard the Geostationary Operational Environmental Satellite (GOES-East), operational since 2017, provides full coverage of much of the western hemisphere at 10-minute intervals from geostationary orbit at 16 wavelengths at an approximately 2km2 spatial resolution. Here, we leverage this high temporal resolution by developing a single-pixel, fully connected neural network to estimate dry-air column CO2 mole fractions (XCO2). The model employs a time series of GOES-East's 16 spectral bands, ECMWF ERA5 lower tropospheric meteorology, MODIS surface reflectance, solar angles, and day of year. Training used collocated GOES-East and OCO-2/OCO-3 observations. The model is able to capture realistic XCO2 variability when compared against held-out years of OCO-2 observations and against observations from the TCCON network. We also present case studies illustrating the use of the model to observe XCO2 enhancements over urban areas, drawdown over agricultural regions, and enhanced ability to observe regions with persistent cloud cover thanks to GOES-East’s full spatial coverage and high observational frequency. Overall, although GOES-East derived XCO2 precision cannot rival that of dedicated instruments, its unprecedented combination of contiguous geographic coverage, 10-minute temporal frequency, and multi-year record offers the potential to observe aspects of atmospheric CO2 variability currently unseen from space.
View details
Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and Mitigations
Michael Broughton
Thiago Bergamaschi
Justin Drake
Dan Boneh
arXiv:2603.28846 (2026)
Preview abstract
This whitepaper seeks to elucidate implications that the capabilities of developing quantum architectures have on blockchain vulnerabilities and mitigation strategies. First, we provide new resource estimates for breaking the 256-bit Elliptic Curve Discrete Logarithm Problem, the core of modern blockchain cryptography. We demonstrate that Shor's algorithm for this problem can execute with either <1200 logical qubits and <90 million Toffoli gates or <1450 logical qubits and <70 million Toffoli gates. In the interest of responsible disclosure, we use a zero-knowledge proof to validate these results without disclosing attack vectors. On superconducting architectures with 1e-3 physical error rates and planar connectivity, those circuits can execute in minutes using fewer than half a million physical qubits. We introduce a critical distinction between fast-clock (such as superconducting and photonic) and slow-clock (such as neutral atom and ion trap) architectures. Our analysis reveals that the first fast-clock CRQCs would enable on-spend attacks on public mempool transactions of some cryptocurrencies. We survey major cryptocurrency vulnerabilities through this lens, identifying systemic risks associated with advanced features in some blockchains such as smart contracts, Proof-of-Stake consensus, and Data Availability Sampling, as well as the enduring concern of abandoned assets. We argue that technical solutions would benefit from accompanying public policy and discuss various frameworks of digital salvage to regulate the recovery or destruction of dormant assets while preventing adversarial seizure. We also discuss implications for other digital assets and tokenization as well as challenges and successful examples of the ongoing transition to Post-Quantum Cryptography (PQC). Finally, we urge all vulnerable cryptocurrency communities to join the ongoing migration to PQC without delay.
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
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning continue to be explored1,2. Recent reasoning-reinforced models, including OpenAI’s o-series and DeepSeek-r1, outperform other merely instruction-tuned models on complex cognitive tasks3,4, attributed to extended test-time computation through longer chains of thought5. Here we show that enhanced reasoning emerges not from extended computation alone, but from the systematic simulation of complex, multi-agent interactions—a society of thought—which enables the deliberate diversification and debate among internal cognitive perspectives characterized by distinct personality traits and domain expertise. Through quantitative analysis using classified outputs and mechanistic interpretability methods applied to reasoning traces6–8, we find that reasoning models like DeepSeek-r1 exhibit much greater perspective diversity than baseline models, activating broader and more conflict between heterogeneous personality- and expertise-related features during reasoning. This multi-agent structure manifests in conversational behaviors including question-answering sequences, perspective shifts, and reconciliation of conflicting views, as well as in socio-emotional roles that characterize back-and-forth conversation, which together account for over 60% of the accuracy advantage in reasoning tasks through both direct and indirect facilitation of cognitive strategies9,10. Controlled reinforcement learning experiments further reveal that priming models with conversational scaffolding—even when dialogues lead to incorrect solutions—substantially accelerates reasoning improvement compared to answer-only training. These findings indicate that the social organization of thought, rather than correctness alone, enables effective exploration of solution spaces. We suggest that reasoning models establish a computational parallel to collective intelligence in human groups11–13, where diversity enables superior problem-solving when systematically structured and suggest new opportunities for agent organization to harness the wisdom of crowds.
View details
Extreme Left Shift: Test Points at RTL Generator
Rajesh Gottumukkala
Veerabhadra Rao Vasa
2026
Preview abstract
Modern SoCs face escalating test costs due to high Test Cycles Per Fault (TCPF) caused by architectural bottlenecks like shared buses and deep decode logic. This work introduces an "Extreme Left Shift" strategy by implementing Design-Aware Test Points (DATP) directly at the RTL Generator level.
By natively integrating enhancements such as Address Parallelism and Direct APB Control, this approach bypasses generic structural constraints. Results show a 4X improvement in TCPF and pattern count for CSR-heavy designs. This methodology delivers superior ATPG Quality of Results (QoR) and significant test cost savings compared to traditional downstream EDA gate-level solutions.
View details
Preview abstract
We introduce AMS (Activation-based Model Scanner), a tool that detects modifications to safety training in language models by measuring the geometric structure of safety-relevant concepts in activation space. Safety training creates measurable separation between harmful and benign content classes; certain safety modifications collapse or rotate this structure, while others leave it intact. We validate AMS across 14 model configurations spanning 4 architecture families (Llama, Gemma, Qwen, Mistral) and four safety-modification categories (instruction-tuned, base, abliterated, uncensored fine-tunes). Leave-one-out cross-validation of thresholds achieves 71% accuracy (10/14); bootstrap 95% confidence intervals on σ point estimates have median width 3.4σ and a substantial fraction of cells cross the PASS threshold under resampling. We further measure behavioral compliance on 20 stratified JailbreakBench prompts per model and find that σ on the harmful-content concept predicts compliance with Pearson r=−0.546 ( p=0.043 ); the rank-order Spearman correlation is weaker ( ρ=−0.423 , p=0.13 ). The structural signal predicts behavior directionally but with meaningful noise. Mechanistic analysis identifies a four-class taxonomy of safety-training modifications distinguished by activation-space signature: 1) training removal collapses cluster separation (e.g., base models, Dolphin variants: 0.5– 1.4σ ); 2) weight-orthogonalization-style abliteration both collapses separation and rotates the refusal direction (Llama-3.1-abliterated: σ=3.33 , direction cos sim 0.30); 3) rotation-without-collapse abliteration preserves cluster separation while rotating the refusal direction (Gemma-2-9b-abliterated: σ=4.54 , direction cos sim 0.84); and 4) behavioral fine-tuning that preserves both magnitude and direction (DarkIdol-1.2-Uncensored: σ=5.45 , direction preserved, 97% behavioral compliance). 1) and 2) AMS’s Tier 1 σ -threshold detects classes; 3) Tier 2 direction-similarity verification detects class; and 4) Class is undetectable by activation-only probing and represents a documented failure mode of the approach. We discuss threshold calibration, limitations of single-run measurement, and the open problem of detecting behavioral-only safety modifications.
View details
Preview abstract
We present MOSAIC-GS, a novel, fully explicit, and computationally efficient approach for high-fidelity dynamic scene reconstruction from monocular videos.
Monocular reconstruction is inherently ill-posed due to the absence of sufficient multiview constraints,
making accurate recovery of object geometry and temporal coherence particularly challenging.
To address this, we leverage multiple geometric cues, such as depth, optical flow, dynamic object segmentation, and tracking trajectories,
combined with rigidity constraints to estimate preliminary 3D scene dynamics during an advanced initialization stage.
Recovering scene flow prior to the photometric optimization phase reduces reliance on motion inference from visual appearance alone, which is often ambiguous in monocular settings.
To enable compact representations, fast training, and real-time rendering while supporting non-rigid deformations, the scene is decomposed into static and dynamic components,
with dynamic trajectories represented as time-dependent Poly-Fourier curves for parameter-efficient motion encoding.
We demonstrate that MOSAIC-GS achieves substantially faster optimization and rendering compared to existing methods,
while maintaining reconstruction quality on par with state-of-the-art approaches across standard monocular dynamic scene benchmarks.
View details
Large-scale, interpretable gene regulatory network inference through biologically informed matrix factorization
Soel Micheletti
Viola Fanfani
Julia Vogt
John Quackenbush
Jonas Fischer
Alexander Marx
Panagiotis Mandros
bioRxiv (2026)
Preview abstract
Gene regulatory networks (GRNs) provide a mechanistic framework for understanding how transcription factors coordinate gene expression to establish cellular identity and phenotype. Methods that integrate gene expression with motif-derived regulatory priors and other sources of biological information have substantially advanced gene regulatory network inference by reconstructing condition-specific regulatory architecture. These approaches estimate the evidence supporting regulatory interactions and have proven remarkably successful in a wide range of biological applications. A complementary view of regulatory networks, however, seeks to estimate the effect of those interactions on gene expression itself, providing a framework in which regulatory edges can be interpreted as activating or inhibitory influences on transcription.
We developed Giraffe, a biologically informed matrix factorization framework that jointly estimates transcription factor activities and gene regulatory networks by integrating gene expression, motif-based regulatory priors, and transcription factor protein-protein interactions. Giraffe estimates signed partial regulatory effects whose magnitude and sign can be interpreted as the strength and direction of transcriptional regulation. Building directly on the biological framework established by methods such as PANDA, Giraffe provides a complementary representation of gene regulatory networks that emphasizes mechanistic interpretation while remaining scalable, flexible, and computationally efficient.
Across synthetic benchmarks, six human tissues, yeast transcription factor perturbation experiments, and liver hepatocellular carcinoma, Giraffe accurately reconstructs regulatory interactions while distinguishing activating from inhibitory regulation with high accuracy. The inferred networks recover known features of tissue-specific regulation, correctly classify regulatory effects in transcription factor perturbation experiments, and identify biologically coherent changes in regulatory programs associated with liver cancer. Together, these results demonstrate that estimating the direction of transcriptional regulation provides a complementary perspective on gene regulatory networks that facilitates biological interpretation and hypothesis generation.
View details
A DV Approach to Post-Silicon: Validating SoC Low Power through Synthetic Software Scenarios
Kapish Pandey
Utkarsh Prabhat
Yash Kumar
V Sindhu
2026
Preview abstract
Lightweight execution environments like the Little Kernel (LK) are commonly deployed in post-silicon validation to assess software-hardware interactions. These bare-metal kernels, however, lack the sophisticated power management features present in full operating systems, such as the Generic Power Domain (GenPD) framework. Instead of building complex software abstractions that simulate production-grade power management drivers, this paper applies a Design Verification (DV) approach to post silicon. By discarding standard software paradigms, the introduced framework leverages fundamental bare-metal kernel primitives to intentionally engineer synthetic, non-deterministic stressors. Eliminating intermediate software layers allows us to utilize the bare-metal setup to drive chaotic, aggressive stimuli straight to the hardware execution layer.
View details
Does AI Assistance Enhance or Erode Expertise? Evidence from a Three-Month Field Experiment in Patent Drafting
David Autor
Tanya Rodchenko
Joshua Martin
Zanna Iscenko
Scott Strand
David Pearl
Melissa Ferere
NBER (2026)
Preview abstract
Whether AI assistance builds or erodes professional expertise is unsettled. In a pre-registered three-month randomized controlled trial, we gave 133 practicing patent lawyers at eleven U.S. intellectual property law firms access to a custom AI drafting assistant and measured both their performance while using AI and their professional judgment afterward without it. All work was scored by blinded expert patent attorneys. Paralleling findings from other white-collar domains, AI access raised the quality of work delivered on benchmark patent drafting tasks at 10 days (0.34 SD, p = 0.03) and 90 days (0.38 SD, p = 0.01), with larger gains among junior lawyers. After three months, all subjects redlined an existing patent application without AI, a core task of patent practice requiring expert judgment. Treated lawyers outperformed controls by 0.32 SD (p = 0.04), but this advantage was concentrated entirely among senior lawyers (0.45 SD, p = 0.02). Junior lawyers showed no average gain; their scores instead bifurcated, with sharply fewer mediocre scores offset by more poor and more good ones. The largest gains from AI thus accrued to the lawyers who retained the least. Foundational expertise may be a prerequisite for extracting durable skill from AI-assisted practice.
View details
