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.

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
1 - 15 of 11927 publications
Who’s Doing the Thinking Now? Reflexivity and Oversight in GenAI-Mediated Decision-Making
Oliver Herrbach
Siddharth Gaurav Majhi
Under review with Information Systems Journal (2027) (to appear)
Preview abstract Generative AI (GenAI) is increasingly embedded in organizational decision-making, reshaping how judgment, oversight, and productivity are enacted in everyday work. While prior research documents performance gains from AI assistance, less is known about how sustained GenAI use affects human reflexivity, i.e., the capacity for critical evaluation, deliberation, and decision override in AI-mediated tasks. This study advances Algorithmic Reflexivity Reallocation Theory (ALERT), which theorizes how repeated algorithmic mediation reallocates cognitive effort away from human judgment through cognitive offloading and automation bias, producing a trade-off between productivity and reflexive oversight. We test ALERT using a three-stage mixed-methods design comprising qualitative grounding interviews, a controlled behavioral experiment, and a large-scale survey-based structural equation model. Behavioral results show that GenAI assistance increases task efficiency but reduces override behavior, particularly when recommendations are plausible yet incorrect. Structural modeling further demonstrates that human–AI trust, task familiarity, and algorithmic structuration predict cognitive offloading, which in turn suppresses override behavior and weakens individual reflexivity while increasing perceived productivity. Transparency emerges as a key design condition that mitigates cognitive offloading and preserves evaluative engagement. By theorizing reflexivity as a reallocatable cognitive and organizational resource, ALERT extends structuration and human–AI interaction research by explaining how productivity gains can coexist with the erosion of reflective judgment under sustained GenAI use. The study contributes a process theory of AI-mediated decision-making with implications for the design and governance of AI-supported work systems. View details
Preview abstract Large Language Models (LLMs) are increasingly deployed to automate enterprise recruitment pipelines, yet evaluating their decision consistency and underlying logic remains heavily throttled by a lack of credible, real-world benchmark datasets. Free-form floating-point scoring methods frequently used in recruitment AI suffer from severe numerical calibration drift and mask the models' intermediate reasoning. To address these challenges, we introduce Djinni-CB, a novel, two-tiered evaluation benchmark containing 2,484 real candidate-job pairs spanning 21 diverse job categories, bridged entirely from naturally occurring, anonymized candidate résumés and standardized employer postings. Rather than relying on generic scores, we implement a rigorous 29-question structured questionnaire across 9 diagnostic groups to audit pure deterministic reasoning boundaries. We establish comprehensive baseline results at temperature T=0.0 comparing frontier model architectures: Gemini 4.1m, DeepSeek Pro, GPT-5.4, and Gemini 2.5 Pro. Over 235,000 discrete decision points reveal a distinct dichotomy in the LLM ecosystem: a "Literal Gatekeeper" cluster (DeepSeek Pro and GPT-5.4) that prioritizes strict keyword matching, and a "Holistic" cluster (the Gemini family) that leverages contextual domain inference. Our dataset provides a highly structured resource complete with verbatim natural-language reasoning logs, offering an essential framework for future research into interpretability, factuality, and consistency in automated hiring. View details
The Decision-Accountability Gap: Symbolic Oversight Theory and Pivot to Human-in-the-Accountability-Loop (HIAL)
Sreekumar Hariharan
Amrita George
Shaliet Rose Sebastian
Sent for review (2027) (to appear)
Preview abstract As organizations increasingly deploy agentic artificial intelligence (AI) systems, Human-in-the-Loop (HITL) oversight structures are widely mandated to ensure compliance, ethics, and control. However, the substantive efficacy of these structures remains poorly understood under conditions of AI scale and high operational complexity. This study introduces Symbolic Oversight Theory (SOT), a novel AI governance framework rooted in neo-institutional theory and bounded rationality. We theorize that when AI systems exhibit high epistemic authority under intense operational velocity and regulatory pressures, traditional decision-centric HITL mechanisms decouple from operational realities. This creates a state of "symbolic oversight"—a ritualistic formality where formal review checkpoints persist for institutional legitimacy, but substantive human cognition, reflexivity, and intervention capacity erode, structurally shifting accountability loads onto individuals without true decisional agency. To validate and apply SOT, we employ a rigorous mixed-method research design across three studies: (1) a controlled behavioral experiment tracking heuristic processing and error-detection among finance professionals, (2) a field survey validating the structural relations and psychometric properties of our constructs, and (3) an empirical study integrating anonymized interaction telemetry logs from internal enterprise agentic AI systems with semi-structured, anonymized internal employee interviews. Our findings demonstrate an empirical divergence between nominal and enacted oversight, showing that symbolic HITL suppresses human reflexivity through cognitive offloading and proceduralization, ultimately yielding a systemic decision-accountability gap. To resolve this governance design failure, we present a design-science architecture shifting governance from decision-centric loops to a consequence-centric Human-in-the-Accountability-Loop (HIAL) framework, establishing new metrics for consequence traceability, accountability latency, and auditability-controllability symmetry. View details
A Data-Driven Biophotonic Skin Model for Wearable Sensing
Kaiyuan (Kai) Yao
Hamed Vavadi
Biomedical Optics Express (2027) (to appear)
Preview abstract Accurate modeling of light-matter interactions in biological tissue is fundamental to the advancement of biophotonic sensing, in-vivo diagnostics, and the development of next-generation wearable health monitors. While computational methods such as Monte Carlo simulations are powerful tools for virtual prototyping, the reliability of their predictions is strictly limited by the fidelity of the underlying skin model. Current industry-standard models primarily rely on optical parameters derived from ex-vivo tissue samples or dataset with limited size and variabilities in measurement methods, often failing to capture the complex spectral responses and inter-subject variability found in living populations. To address this limitation, we present a data-driven biophotonic skin model rigorously calibrated and validated against extensive in-vivo dataset. Our study utilizes smartwatch data acquired across a broad spectral range (UV to SWIR) and multiple sensor geometries, with subjects covering a diverse range of skin tones. By grounding the standard multilayer skin architecture in experimental data, this work provides a robust, statistically validated foundation for the design, simulation, and optimization of future wearable optical sensors. View details
Preview abstract Enterprise digital transformation projects are among the most complex and costly initiatives in modern organizations, yet conventional governance frameworks rely predominantly on reactive, lagging indicators of project health. This paper presents an empirical binary classification study applying machine learning to identify high-risk implementations in enterprise digital transformation portfolios. A publicly available dataset of 4,000 project records encoding 49 governance-relevant features is used; an original four-level risk taxonomy is collapsed into two governance-actionable classes: High-Risk and Not High-Risk Implementation. This study proposes a governance-actionable machine learning framework that converts multi-level project risk into binary escalation decisions and combines cross-validated model selection with direct SHAP attribution for enterprise transformation portfolios. Seven classifiers are benchmarked against a majority-class baseline across six metrics. Model selection incorporates five-fold stratified cross-validation and grid-search hyperparameter optimization for the two strongest classifiers. Five-fold stratified cross-validation confirms generalization stability across all models: AdaBoost achieves the highest cross-validation performance—85.85% ± 1.46% accuracy, 85.56% ± 1.32% balanced accuracy, 84.02% ± 1.36% F1-score, and 0.9380 ± 0.0070 ROC-AUC—and also leads on the held-out test set (90.87% accuracy, 90.69% balanced accuracy, 89.76% F1-score, 0.9766 ROC-AUC). All seven classifiers exhibit standard deviations below the 3.0 percentage-point instability threshold, confirming robust generalization without overfitting. SHAP-based explainability, applied directly to the AdaBoost model via TreeExplainer, identifies Complexity_Score, Org_Process_Maturity, and Technology_Familiarity as the primary drivers of high-risk classification, consistent with digital transformation governance literature. Practical integration scenarios for portfolio dashboards and governance escalation workflows are discussed. View details
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
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
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
Preview abstract In modern digital System-on-Chip (SoC) designs, sequential standard cells—such as single-bit D-Flip-Flops (DFFs) and Multibit Flip-Flops (MBFFs)—serve as fundamental building blocks for memory arrays, registers, and pipelines. To meet ultra-low-power requirements in mobile, edge, and high-performance computing (HPC) applications, these circuits increasingly operate at near-threshold supply voltages (VDD0.45-0.50V). However, aggressive voltage scaling introduces critical failure mechanisms: Write-Back Failures: At low supply voltages, transmission gate or pass-gate write paths fail to overpower cross-coupled feedback inverters, preventing state transitions and causing cells to retain stale values. Hold-Time/Race Violations: Clock skew and fast transitions trigger internal races. When process variation weakens clock gating or feedback control, internal storage nodes degrade, leading to transient glitches, state corruption, or functional failure. To verify standard cell reliability, brute-force Monte Carlo (MC) simulations are computationally prohibitive, requiring billions of SPICE iterations. This work outlines a High-Sigma Verification (HSV) methodology using advanced statistical sampling—such as Importance Sampling, Boundary Search, or machine-learning-driven MC—to evaluate rare, extreme variation tails with a fraction of the computational overhead. By mapping the multidimensional local variation space, the framework calculates true statistical yield margins (the "sigma-metric") and identifies dominant transistor-level variation sources, including pull-up/pull-down network balance and pass-gate drive strength. Beyond single-point analyses, the workflow bridges layout-level parasitic extraction and silicon-level yield predictability by scaling high-sigma evaluation across comprehensive PVT corners and diverse input slew/output load profiles. This multi-corner, slew-aware verification captures tail-distribution failures and dynamic delay non-linearities under extreme operating conditions, delivering characterization-ready yield bounds for robust, near-threshold SoC sign-off. View details
Preview abstract Much-maligned AI token leaderboards are often seen to encourage tokenmaxxing. Is it possible to design a token leaderboard with positive impact? View details
Balancing AI tensions: Moving from AI adoption to effective SDLC use
Jessica Baolin (Lin)
Nathen Harvey
DORA (2026)
Preview abstract Using AI in the software development life cycle (SDLC) is quickly becoming an industry standard. The 2025 DORA State of AI-assisted Software Development report found that 90% of technology professionals now use AI at work, and over 80% believe it has increased their productivity. Beneath these impressive top-line numbers, a more complex reality is emerging. Extensive qualitative analysis of enterprise software engineers reveals that AI's impact on the SDLC is not a simple linear improvement. Instead, it presents a series of profound tradeoffs. While AI successfully accelerates initial code generation and reduces the friction of starting new tasks, the time saved in creation is frequently re-allocated to a new hidden tax: high-scrutiny auditing and verification. This article explores four key tradeoffs of AI adoption, and provides actionable strategies to balance them. View details
Preview abstract The promise of tailored agent behavior is undermined by a critical explainability challenge: it is difficult to assess how closely and consistently the agent follows user-defined rules. As Large Language Models (LLMs) transition from static assistants to autonomous agents, developers have pioneered markdown-based rule files (e.g., GEMINI.md, CIDER_AGENT.md) to steer agent behavior and mitigate a "organizational context gap" that emerges when general-purpose models lack the "organizational context" necessary for contextually relevant results. This paper presents a qualitative study of 12 Google software developers (n=12) to investigate the authoring and efficacy of these agent rules. Our findings reveal that while rules are intended as technical steering mechanisms, they function as a "Black Box" of validation, where 12/12 participants rely on anecdotal "vibe checks" due to a profound lack of formal evaluation and explainability frameworks. We identify this opacity as a systemic Attribution Gap, which prevents developers from discerning whether a successful outcome was the result of deliberate logic or "pure luck." Paradoxically, these files serve a dual role as "Living Documentation," bridging technical instruction for AI with sociotechnical onboarding for humans. We argue for a transition toward library-level governance and rigorous traceability to transform agent customization from an ad-hoc craft into a human-centered science by revealing the internal "seams" of rule interpretation. View details
Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
José Cambronero
Renyao Wei
Grant Uy
Chin-Jung Liu
Shiying Pan
Satish Chandra
ICSE-SEIP '26: Proceedings of the IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice, ACM (Association for Computing Machinery), New York, NY, USA (2026), 118 – 129
Preview abstract Agentic automated program repair (APR) is increasingly being used to tackle complex, repository-level bugs in both academic and industry settings. However, changes made by the agent still need to be reviewed by a human before committing them to the codebase to ensure the change correctly fixes the bug. Showing unlikely patches to developers can lead to substantial noise, wasting valuable developer time and decreasing trust in all automated code changes. We introduce two complementary LLM-based policies to reduce such noise: bug abstention and patch critic policies. Bug abstention allows us to exclude bugs that the agentic APR system is unlikely to fix and the patch critic rejects patches that are unlikely to be a good fix for the given bug. We evaluate both policies on three sets of bugs collected from Google’s codebase and agent trajectories generated by an agentic APR system in use at Google. We introduce filtered success rates, where we compute performance after removing trajectories rejected by our policies. On a set of 174 human-reported bugs, abstention and critic can raise filtered success rates up to 13 percentage points and 15 percentage points, respectively, and up to 29 percentage points in combination. For null pointer exceptions and sanitizer-reported bugs with machine-generated bug reports or known reproduction tests, we show the same critic policy can be used to improve average single-sample success rates. View details
Preview abstract We show that a simple scoring-based tie-breaking can help improve lower bounds for the expansion (aka isoperimetric number) of random regular graphs with small even degrees. Specifically, for degrees 4, 6 and 8, we show that, with high probability, the expansions are at least 0.489, 1.120 and 1.813 respectively. View details
Preview abstract Accurate, actionable climate information at kilometer scales is crucial for robust natural hazard risk assessment and infrastructure planning. Simulating the impact of climate at these resolutions remains intractable, forcing reliance on downscaling, either physics-based or statistical methods which transform climate simulations from coarse to impact-relevant resolutions. It is essential to comprehensively capture the interdependency among climate processes of interest. However, current approaches, either lack the desired scalability or are bespoke to specific types of hazards. We introduce GenFocal, a step change in paradigm. GenFocal is a computationally efficient, general-purpose, end-to-end probabilistic, generative framework that gives rise to full probabilistic characterizations of complex climate processes interacting at fine spatiotemporal scales. When employed to assess risk in the present climate, GenFocal more faithfully projects the risk of extremes than state-of-the-art approaches including one recommended by the US Fifth National Climate Assessment. GenFocal produces plausible tracks of tropical cyclones, providing accurate statistics of their genesis and evolution, even when they are absent from the corresponding climate simulations. GenFocal also shows compelling results that are consistent with the literature on projecting climate impact in an extended time frame (five decades to one century). In short, GenFocal transforms the numerical computation into statistical knowledge bases that can be efficiently queried, thus opening up new possibilities of assessing the impacts of future climates at the spatio-temporal scales relevant to local and regional communities. We believe this work, as a starting point, establishes generative AI technology as an effective and potent paradigm for modeling complex, high-dimensional multivariate statistical correlations that have deterred precise quantification of climate risks associated with hazards such as wildfires, extreme heat, tropical cyclones, and flooding; thereby enabling the evaluation of adaptation strategies for affected populations and the built environment. View details
×