Neural Quantum States (NQS) are powerful variational representations of quantum many-body wavefunctions, yet their performance depends sensitively on the chosen basis. Using an exactly solvable one-dimensional Ising model, we show that local basis rotations leave the minimization landscape unchanged while relocating the exact ground state in parameter space. This provides a controlled framework to disentangle representational limitations from optimization-induced trainability effects. This geometric displacement, quantified through information-geometric measures, can steer optimization of shallow architectures toward saddle points and high-curvature regions. As a result, low energy errors may coexist with an incorrect wavefunction structure. By comparing energy and infidelity optimization within the same variational architectures, we show that optimization failure can persist even when the rotated target state remains representable. Our results identify a geometric mechanism contributing to basis dependence in NQS and motivate landscape-aware variational design.

Representations pervade our daily experience, from letters representing sounds to bit strings encoding digital files. While such representations require externally defined decoders to convey meaning, conscious experience is fundamentally different: a neural state corresponding to perceiving a red square cannot alternatively encode the experience of a green triangle. This intrinsic property of consciousness suggests that conscious representations must be unambiguous in a way that conventional representations are not. We formalize this intuition using information theory, defining representational ambiguity as the conditional entropy H(I|R) over possible interpretations I given a representation R. Through experiments on neural networks trained to classify MNIST digits, we demonstrate that relational structures in network connectivity can unambiguously encode representational content. From relational structure alone, we achieve perfect (100%) accuracy for dropout-trained networks and 38% for standard backpropagation (chance: 10%) in identifying output neuron class identity, despite identical task performance, demonstrating that representational ambiguity can arise orthogonally to behavioral accuracy. We further show that spatial position of input neurons, relevant to phenomenal properties like visual field location, can be decoded from network connectivity with R^2 up to 0.844. These results provide a quantitative method for measuring representational ambiguity in neural systems and demonstrate that neural networks can exhibit the low-ambiguity representations posited as necessary (though not sufficient) by theoretical accounts such as narrow representationalism and IIT.

Operator models are regression algorithms between Banach spaces of functions. They have become an increasingly critical tool for spatiotemporal forecasting and physics emulation, especially in high-stakes scenarios where robust, calibrated uncertainty quantification is required. We introduce Local Sliced Conformal Inference (LSCI), a distribution-free framework for generating function-valued, locally adaptive prediction sets for operator models. We prove finite-sample validity and derive a data-dependent upper bound on the coverage gap under local exchangeability. On synthetic Gaussian-process tasks and real applications (air quality monitoring, energy demand forecasting, and weather prediction), LSCI yields tighter sets with stronger adaptivity compared to conformal baselines. We also empirically demonstrate robustness against biased predictions and certain out-of-distribution noise regimes.

Large language models (LLMs) have demonstrated promising performance in both automatic speech recognition (ASR) and text-to-speech (TTS) systems, gradually becoming the mainstream approach. However, most current approaches address these tasks separately rather than through a unified framework. This work aims to integrate these two tasks into one unified model. Although discrete speech tokenization enables joint modeling, its inherent information loss limits performance in both recognition and generation. In this work, we present UniVoice, a unified LLM framework through continuous representations that seamlessly integrates speech recognition and synthesis within a single model. Our approach combines the strengths of autoregressive modeling for speech recognition with flow matching for high-quality generation. To mitigate the inherent divergence between autoregressive and flow-matching models, we further design a dual attention mechanism, which switches between a causal mask for recognition and a bidirectional attention mask for synthesis. Furthermore, the proposed text-prefix-conditioned speech infilling method enables high-fidelity zero-shot voice cloning. Experimental results demonstrate that our method can achieve or exceed current single-task modeling methods in both ASR and zero-shot TTS tasks. This work explores new possibilities for end-to-end speech understanding and generation. Code is available at https://github.com/gwh22/UniVoice.

Signal Temporal Logic (STL) is an expressive language for specifying behaviors of dynamical systems from continuous signals. However, a limitation of standard STL is its inherently deterministic semantics, which prevents it from accommodating uncertainty. Existing approaches to overcome this limitation are computationally costly and limit real-time capability, requiring repeated trajectory sampling or the redesign of probability distributions over atomic propositions whenever the atomic propositions or specifications change. We introduce pacSTL, a framework that combines Probably Approximately Correct (PAC)-bounded reachable set predictions with an interval extension of STL. pacSTL computes lower and upper bounds on atomic robustness values by solving optimization problems over PAC-bounded reachable sets and propagates the bounds through the temporal logic operators. The resulting evaluation yields a PAC-bounded robustness interval at the specification level. We demonstrate the efficiency and relevance of pacSTL by verifying a quadrotor flight scenario and runtime monitoring a maritime navigation specification.

Network pruning is used to reduce inference latency and power consumption in large neural networks. However, most methods focus on empirical results at the expense of understanding the pruning process. We introduce Hyperflux, a novel $L_0$ method which models pruning as a continuously evolving system determined by flux, the gradient response to a weight's removal, and pressure, a global regularization driving weights toward pruning. By exploiting this model, Hyperflux's pruning behavior becomes understandable at both microscopic (weight regrowth/pruning) and macroscopic (sparsity convergence, etc.) levels. We also introduce a novel pressure scheduler that reliably targets desired sparsities. Hyperflux achieves competitive results with ResNet-50, VGG-19 and DeiT-T/S on CIFAR-10, CIFAR-100 and ImageNet datasets.

Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de facto mode of interaction with LLMs for completing long and complex tasks. While LLM capabilities continue to improve, they remain increasingly susceptible to jailbreaking, especially in multi-turn scenarios where harmful intent can be subtly injected across the conversation to produce nefarious outcomes. While single-turn attacks have been extensively explored, adaptability, efficiency and effectiveness continue to remain key challenges for their multi-turn counterparts. To address these gaps, we present PLAGUE, a novel plug-and-play framework for designing multi-turn attacks inspired by lifelong-learning agents. PLAGUE dissects the lifetime of a multi-turn attack into three carefully designed phases (Primer, Planner and Finisher) that enable a systematic and information-rich exploration of the multi-turn attack family. Evaluations show that red-teaming agents designed using PLAGUE achieve state-of-the-art jailbreaking results, improving attack success rates (ASR) by more than 30% across leading models in a lesser or comparable query budget. Particularly, PLAGUE enables an ASR (based on StrongReject) of 81.4% on OpenAI's o3 and 67.3% on Claude's Opus 4.1, two models that are considered highly resistant to jailbreaks in safety literature. Our work offers tools and insights to understand the importance of plan initialization, context optimization and lifelong learning in crafting multi-turn attacks for a comprehensive model vulnerability evaluation.

Many researchers apply classical statistical decision theory to evaluate treatment choices and learn optimal policies. However, because this framework relies solely on realized outcomes under chosen actions and ignores counterfactuals, it cannot assess the quality of a decision relative to feasible alternatives at the unit level, which is an important requirement in some settings. For example, in pretrial bail decisions, a judge must balance crime prevention upon release against the risk of imposing unnecessary burdens on arrestees. A central challenge in this framework is identification: since only one potential outcome is observed per unit, counterfactual risk is typically not identifiable. We show that, under strong ignorability, counterfactual risk is identifiable if and only if the loss is additive in the potential outcomes. We further demonstrate that additive counterfactual losses can yield treatment recommendations that differ from those based on standard losses when more than two treatment options are available. We show that additive counterfactual losses capture not only decision accuracy but also decision difficulty, whereas standard losses reflect accuracy alone. Finally, we introduce a symbolic linear inverse program that determines whether a given counterfactual loss yields an identifiable risk, without requiring data.

We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model selection: (i) non-identifiability of gating parameters up to common translations, (ii) intrinsic gate-expert interactions that induce coupled differential relations in the likelihood, and (iii) the tight numerator-denominator coupling in the softmax-induced conditional density. Our approach introduces Voronoi-type loss functions aligned with the gate-partition geometry and establishes finite-sample convergence rates for the maximum likelihood estimator (MLE). In over-specified models, we reveal a link between the MLE's convergence rate and the solvability of an associated system of polynomial equations characterizing near-nonidentifiable directions. For model selection, we adapt dendrograms of mixing measures to SGMoE, yielding a consistent, sweep-free selector of the number of experts that attains pointwise-optimal parameter rates under overfitting while avoiding multi-size training. Simulations on synthetic data corroborate the theory, accurately recovering the expert count and achieving the predicted rates for parameter estimation while closely approximating the regression function. Under model misspecification (e.g., $ε$-contamination), the dendrogram selection criterion is robust, recovering the true number of mixture components, while the Akaike information criterion, the Bayesian information criterion, and the integrated completed likelihood tend to overselect as sample size grows. On a maize proteomics dataset of drought-responsive traits, our dendrogram-guided SGMoE selects two experts, exposes a clear mixing-measure hierarchy, stabilizes the likelihood early, and yields interpretable genotype-phenotype maps, outperforming standard criteria without multi-size training.

Decoding sensory experiences from neural activity to reconstruct human-perceived visual stimuli and semantic content remains a challenge in neuroscience and artificial intelligence. Despite notable progress in current brain decoding models, a critical gap still persists in their systematic integration with established neuroscientific theories and the exploration of underlying neural mechanisms. Here, we present a novel framework that directly decodes fMRI signals into textual descriptions of viewed natural images. Our novel deep learning model, trained without visual information, achieves state-of-the-art semantic decoding performance, generating meaningful captions that capture the core semantic content of complex scenes. Neuroanatomical analysis reveals the critical role of higher-level visual cortices, including MT+ complex, ventral stream visual cortex, and inferior parietal cortex, in visual semantic processing. Furthermore, category-specific analysis demonstrates nuanced neural representations for semantic dimensions like animacy and motion. This work provides a more direct and interpretable framework to the brain's semantic decoding, offering a powerful new methodology for probing the neural basis of complex semantic processing, refining the understanding of the distributed semantic network, and potentially developing brain-inspired language models.

Current quantum computers require algorithms that use limited resources economically. In quantum machine learning, success hinges on quantum feature-maps, which embed classical data into the state space of qubits. We introduce Quantum Feature-Map Learning via Analytic Iterative Reconstructions (Q-FLAIR), an algorithm that reduces quantum resource overhead in iterative feature-map circuit construction. It shifts workloads to a classical computer via partial analytic reconstructions of the quantum model, using only a few evaluations. For each probed gate addition to the ansatz, the simultaneous selection and optimization of the data feature and weight parameter is then entirely classical. Integrated into quantum neural network and quantum kernel support vector classifiers, Q-FLAIR shows state-of-the-art benchmark performance. Since resource overhead decouples from feature dimension, we train a quantum model on a real IBM device in only four hours, surpassing 90% accuracy on the full-resolution MNIST dataset (784 features, digits 3 vs 5). Such results were previously unattainable, as the feature dimension prohibitively drives hardware demands for fixed and search costs for adaptive ansätze. Furthermore, Q-FLAIR demonstrates de-quantization robustness against direct classical modeling, satisfying a benchmark rare in the literature and a necessary condition for potential quantum advantage. By rethinking feature-map learning beyond black-box optimization, this work takes a concrete step toward enabling quantum machine learning for real-world problems and near-term quantum computers.

We study the fundamental problem of calibrating a linear binary classifier of the form $σ(\hat{w}^\top x)$, where the feature vector $x$ is Gaussian, $σ$ is a link function, and $\hat{w}$ is an estimator of the true linear weight $w^\star$. By interpolating with a noninformative $\textit{chance classifier}$, we construct a well-calibrated predictor whose interpolation weight depends on the angle $\angle(\hat{w}, w_\star)$ between the estimator $\hat{w}$ and the true linear weight $w_\star$. We establish that this angular calibration approach is provably well-calibrated in a high-dimensional regime where the number of samples and features both diverge, at a comparable rate. The angle $\angle(\hat{w}, w_\star)$ can be consistently estimated. Furthermore, the resulting predictor is uniquely $\textit{Bregman-optimal}$, minimizing the Bregman divergence to the true label distribution within a suitable class of calibrated predictors. Our work is the first to provide a calibration strategy that satisfies both calibration and optimality properties provably in high dimensions. Additionally, we identify conditions under which a classical Platt-scaling predictor converges to our Bregman-optimal calibrated solution. Thus, Platt-scaling also inherits these desirable properties provably in high dimensions.

In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted cryptographic backdoor enables powerful and invisible attack on the NN. Considering the defense, we present applications: first, a provably robust NN watermarking scheme; second, a protocol for guaranteeing user authentication; and third, a protocol for tracking unauthorized sharing of the NN intellectual property (IP). From a broader theoretical perspective, borrowing the ideas from Goldwasser et. al. [FOCS 2022], our main contribution is to show that all these instantiated practical protocol implementations are provably robust. The protocols for watermarking, authentication and IP tracking resist an adversary with black-box access to the NN, whereas the backdoor-enabled adversarial attack is impossible to prevent under the standard assumptions. While the theoretical tools used for our attack is mostly in line with the Goldwasser et. al. ideas, the proofs related to the defense need further studies. Finally, all these protocols are implemented on state-of-the-art NN architectures with empirical results corroborating the theoretical claims. Further, one can utilize post-quantum primitives for implementing the cryptographic backdoors, laying out foundations for quantum-era applications in machine learning (ML).

Cross-disciplinary communication is often hindered by specialized language (i.e., jargon) and uneven background knowledge. Recent advances in speech-to-text and large language models make it possible to provide jargon support during online meetings, but generic support (i.e., defining the same terms for everyone) can overwhelm listeners with definitions they do not need. We present ParseJargon, a system for personalized jargon support in real-time online meetings. We begin with an initial prototype to probe the use of single-sentence user profiles for personalization. We conducted a controlled study and showed that even this minimal personalization enhanced listeners' comprehension and engagement over generic support because of more precise jargon identification. Guided by insights from participants' feedback, we refined the system with more advanced personalization techniques, including in-session user feedback and portable glossary-based profiles. We evaluated how these techniques can further improve jargon identification precision using data collected in the controlled study to simulate personalization over time. We also conducted a latency test, complemented by a lightweight deployment, to analyze the system's real-time capability and usability.

We study decentralized online Riemannian optimization over manifolds with possibly positive curvature, going beyond the Hadamard manifold setting. Decentralized optimization techniques rely on a consensus step that is well understood in Euclidean spaces because of their linearity. However, in positively curved Riemannian spaces, a main technical challenge is that geodesic distances may not induce a globally convex structure. In this work, we first analyze a curvature-aware Riemannian consensus step that enables a linear convergence beyond Hadamard manifolds. Building on this step, we establish a $O(\sqrt{T})$ regret bound for the decentralized online Riemannian gradient descent algorithm. Then, we investigate the two-point bandit feedback setup, where we employ computationally efficient gradient estimators using smoothing techniques, and we demonstrate the same $O(\sqrt{T})$ regret bound through the subconvexity analysis of smoothed objectives.

Designing polynomial-time algorithms for approximate Nash equilibria (ANE) with provable worst-case guarantees is a fundamental open problem in algorithmic game theory. While large language models (LLMs) can generate candidate algorithms at scale, certifying worst-case guarantees requires formal analysis over all game instances -- a task for which no automated system previously existed. Here, we present LegoNE, a framework encoding expert proof strategies into a symbolic language that automatically compiles any candidate algorithm into a finite optimization problem certifying its worst-case guarantee. Integrating LegoNE with a reasoning LLM, we rediscovered an algorithm matching the best polynomial-time guarantee for two-player games, and discovered a three-player algorithm improving the best guarantee from $0.6+δ$ to $0.5+δ$ -- provably beyond the reach of the extension technique, the only previously known multi-player ANE design paradigm. These results show that encoding domain-specific proof strategies into a machine-tractable language can support LLM-driven discovery of algorithms outside known human design paradigms.

Model fingerprinting has emerged as a crucial mechanism for safeguarding the intellectual property of open-source models, offering a non-intrusive approach that requires no modifications to the protected model. However, our analysis reveals that existing fingerprinting techniques are fundamentally vulnerable to false claim attacks, wherein adversaries can fraudulently assert ownership over independent third-party models. We demonstrate that this vulnerability stems from the untargeted nature of current methods, which evaluate model similarity based on arbitrary sample outputs rather than alignment with a specific, predefined reference. To mitigate this vulnerability, we introduce FIT-Print, a targeted fingerprinting paradigm that actively counters false claim attacks. Specifically, FIT-Print leverages optimization to transform the fingerprint into a verifiable, targeted signature. Building upon this foundation, we propose two black-box fingerprinting methods, the bit-wise FIT-ModelDiff and the list-wise FIT-LIME, which utilize output distances and feature attributions as robust model signatures, respectively. Extensive evaluations across benchmark models and datasets show that our framework perfectly neutralizes false claim attacks (100% defense success rate) and eliminates false alarms on independent models (0.0%), all while maintaining a 100% ownership verification rate against diverse model reuse techniques.

We introduce AMix-1, a powerful protein foundation model built on Bayesian Flow Networks and empowered by a systematic training methodology, encompassing pretraining scaling laws, emergent capability analysis, in-context learning mechanism, and test-time scaling algorithm. To guarantee robust scalability, we establish a predictive scaling law and reveal the progressive emergence of structural understanding via loss perspective, culminating in a strong 1.7-billion model. Building on this foundation, we devise a multiple sequence alignment (MSA)-based in-context learning strategy to unify protein design into a general framework, where AMix-1 recognizes deep evolutionary signals among MSAs and consistently generates structurally and functionally coherent proteins. This framework enables the successful design of a dramatically improved AmeR variant with an up to $50\times$ activity increase over its wild type. Pushing the boundaries of protein engineering, we further empower AMix-1 with an evolutionary test-time scaling algorithm for in silico directed evolution that delivers substantial, scalable performance gains as verification budgets are intensified, laying the groundwork for next-generation lab-in-the-loop protein design.

The increasing demand for flexible automation has accelerated the adoption of heterogeneous automated guided vehicles (AGVs). This work investigates a new scheduling problem in a material transportation system consisting of attachable heterogeneous AGVs, including carriers and shuttles, that flexibly attach and detach for cooperative task execution. While such collaboration enhances operational efficiency, the attachment-induced synchronization renders the system highly coupled and susceptible to deadlocks. To address this, we propose a Petri net (PN)-based deadlock-free scheduling framework integrated into an adaptive large neighborhood search (ALNS) algorithm. The PN is introduced to map candidate solutions from static permutations into dynamic collaborative processes, enabling performance evaluation via state evolution and proactive deadlock prevention through structural analysis. Extensive experiments on real-world and synthetic instances demonstrate that the proposed framework significantly improves computational efficiency, with the developed ALNS outperforming the current on-site policy, exact solvers, and state-of-the-art metaheuristics. Finally, sensitivity analysis yields managerial insights for optimal fleet sizing.

The integration of Artificial Intelligence (AI) into corporate strategy has become critical for organizations seeking to maintain competitive advantage in the digital age. Although organizations increasingly rely on AI as a strategic and organizational resource, existing C-suite roles remain only partially equipped to govern, integrate, and leverage it coherently at the enterprise level. Organizations vary in their responses. Some create a dedicated Chief AI Officer (CAIO), others extend existing mandates into hybrid roles, and still others coordinate AI through federated structures. This paper develops a role-design theory to explain this variation. I identify three properties that distinguish AI from earlier cross-cutting enterprise technologies - distributed accountability for judgment, upstream governance, and non-stationarity - and three configurations through which organizations respond: concentrated extension, distributed extension, and role creation. The CAIO Framework links these properties to the executive design problems they generate and to the functions and capabilities required of the dedicated role. Four propositions specify when a dedicated CAIO emerges, what form an organization's response takes, when the dedicated role is effective, and how configurations evolve over time. This paper contributes to research on executive leadership, organizational design, and digital governance by offering a theory-driven account of the strategic integration of AI at the executive level.

As multimedia content expands, the demand for unified multimodal retrieval (UMR) in real-world applications increases. Recent work leverages multimodal large language models (MLLMs) to tackle this task. However, their large parameter size results in high training costs and low inference efficiency. To address this, we propose PUMA: a Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning. Our approach improves UMR from both structural and learning perspectives. (1) Structurally, we propose Layer-Pruned Self-Distillation, which prunes MLLMs by keeping only shallow layers while distilling features from dropped deep layers as teacher signals. This reduces parameters and preserves representation capability. (2) On the learning side, we introduce Modality-Adaptive Contrastive Learning Loss (MAC-Loss), which separates in-batch negatives into harder intra-modality and easier inter-modality groups based on the target modality, assigning different temperature strategies to enhance learning efficiency. Experiments show our method significantly reduces resource usage while maintaining strong performance.

Event cameras provide superior temporal resolution, dynamic range, energy efficiency, and pixel bandwidth. Spiking Neural Networks (SNNs) naturally complement event data through discrete spike signals, making them ideal for event-based tracking. However, current approaches combining Artificial Neural Networks (ANNs) and SNNs suffer from suboptimal architectures that compromise energy efficiency and limit tracking performance. To address these limitations, we propose the first Transformer-based \textbf{S}pike-\textbf{D}riven \textbf{T}racking (SDTrack) pipeline. It incorporates a novel event frame aggregation method called Global Trajectory Prompt (GTP) and a Transformer-based tracker. The GTP method effectively captures global trajectory information and aggregates it with event streams into event frames to enhance spatiotemporal representation. The Transformer-based tracker comprises a fully spike-driven SNN backbone and a simple tracking head. The SDTrack pipeline operates end-to-end without data augmentation or post-processing. Extensive experiments demonstrate that our SDTrack-Tiny pipeline achieves competitive accuracy with only 19.61$M$ parameters and 8.16$mJ$ energy consumption, while our Base version achieves state-of-the-art accuracy across three datasets. Our work establishes a solid foundation for future neuromorphic vision research.

Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance. This creates a need for principled prefiltering procedures that a data provider can apply to protect the accuracy of a range of potential downstream statistical and learning procedures simultaneously. In this work, we formalize and analyze Learner-Agnostic Robust data Prefiltering (LARP), the problem of designing prefiltering procedures with guarantees on the worst-case loss over a pre-specified set of learners. We establish the feasibility of LARP in two theoretical settings, by providing upper-bound guarantees on the worst-case loss. Our theoretical results indicate that protecting heterogeneous learner sets via LARP comes at the price of some performance loss compared to individual, learner-specific prefiltering; we call this gap the price of LARP. To assess this gap in performance, we empirically measure the price of LARP across image and tabular tasks. We further explore potential benefits of LARP from the perspective of saving on repeated data curation efforts, in a game-theoretic model where the downstream learners can split the cost of the single prefiltering.

Recent advances in large-scale text-to-image models have revolutionized creative fields by generating visually captivating outputs from textual prompts; however, while traditional photography offers precise control over camera settings to shape visual aesthetics - such as depth-of-field via aperture - current diffusion models typically rely on prompt engineering to mimic such effects. This approach often results in crude approximations and inadvertently alters the scene content. In this work, we propose Bokeh Diffusion, a scene-consistent bokeh control framework that explicitly conditions a diffusion model on a physical defocus blur parameter. To overcome the scarcity of paired real-world images captured under different camera settings, we introduce a hybrid training pipeline that aligns in-the-wild images with synthetic blur augmentations, providing diverse scenes and subjects as well as supervision to learn the separation of image content from lens blur. Central to our framework is our grounded self-attention mechanism, trained on image pairs with different bokeh levels of the same scene, which enables blur strength to be adjusted in both directions while preserving the underlying scene. Extensive experiments demonstrate that our approach enables flexible, lens-like blur control, supports downstream applications such as real image editing via inversion, and generalizes effectively across both Stable Diffusion and FLUX architectures.

This paper focuses on Geodesic Principal Component Analysis (GPCA) on a collection of probability distributions using the Otto-Wasserstein geometry. The goal is to identify geodesic curves in the space of probability measures that best capture the modes of variation of the underlying dataset. We first address the case of a collection of Gaussian distributions, and show how to lift the computations in the space of invertible linear maps. For the more general setting of absolutely continuous probability measures, we leverage a novel approach to parameterizing geodesics in Wasserstein space with neural networks. Finally, we compare to classical tangent PCA through various examples and provide illustrations on real-world datasets.

In this paper, we focus on the matching recovery problem between a pair of correlated Gaussian Wigner matrices with a latent vertex correspondence. We are particularly interested in a robust version of this problem such that our observation is a perturbed input $(A+E,B+F)$ where $(A,B)$ is a pair of correlated Gaussian Wigner matrices and $E,F$ are adversarially chosen matrices supported on an unknown $εn * εn$ principal minor of $A,B$, respectively. We propose an approximate message passing (AMP) type iterative algorithm that succeeds in polynomial time as long as the correlation $ρ$ between $(A,B)$ is a non-vanishing constant and $ε= o\big( \tfrac{1}{(\log n)^{20}} \big)$. A key distinction from standard AMP is the introduction of a time-dependent matrix multiplication step within the iteration, which simultaneously enlarges the feature dimension and cancels the correlation during the iteration. The main methodological inputs for our result are the iterative random graph matching algorithm proposed in \cite{DL22+, DL23+} and the spectral preprocessing procedure proposed in \cite{IS24+}. To the best of our knowledge, our algorithm is the first efficient random graph matching type algorithm that is robust under any adversarial perturbations of $n^{1-o(1)}$ size.

Retrieval-Augmented Generation (RAG) improves the reliability of large language models by integrating external knowledge, but serving RAG pipelines efficiently is challenging because requests traverse heterogeneous components spanning LLM inference, databases, and CPU-side processing. We present Harmonia, an end-to-end RAG serving framework that addresses these bottlenecks through (i) a flexible pipeline specification interface for composing custom workflows, (ii) heterogeneity-aware deployment that provisions and configures components as a distributed inference system, and (iii) a closed-loop runtime controller that monitors load and execution progress and reduces SLO violations through request prioritization and auto-scaling. Across four RAG applications, Harmonia outperforms commercial alternatives, improving throughput by more than 2.04x while reducing SLO violations by up to 78.4 percent.

A central question in vector- and function-valued learning is how to design kernels that capture both local and non-local interactions while remaining computationally tractable. Existing operator-valued kernels offer only partial answers: separable kernels are efficient but fail to model interactions across the function domain, while commutative kernels capture only pointwise structure. To address this, we propose spectral truncation kernels, a new class of positive definite kernels for vector- and function-valued learning based on spectral truncation and $C^*$-algebra. By allowing noncommutative products in the kernel construction, the proposed kernels induce interactions across the data function domain and fill the gap between existing separable and commutative kernels. In addition, by using the $C^*$-algebraic framework, we reduce the computational cost compared to the existing vector-valued RKHS framework with operator-valued kernels.

A piping and instrumentation diagram (P&ID) is a central reference document in chemical process engineering. Currently, chemical engineers manually review P&IDs through visual inspection to find and rectify errors. However, engineering projects can involve hundreds to thousands of P&ID pages, creating a significant revision workload. This study proposes a rule-based method to support engineers with error detection and correction in P&IDs. The method is based on a graph representation of P&IDs, enabling automated error detection and correction, i.e., autocorrection, through rule graphs. We use our pyDEXPI Python package to generate P&ID graphs from DEXPI-standard P&IDs. In this study, we developed 33 rules based on chemical engineering knowledge and heuristics, with five selected rules demonstrated as examples. A case study on an illustrative P&ID validates the reliability and effectiveness of the rule-based autocorrection method in revising P&IDs.

Artificial Intelligence (AI) is transforming the nature of work, yet there is limited empirical evidence on how it affects demand for human skills. This paper examines whether AI adoption increases the prevalence and value of human capabilities that complement technical AI skills, such as analytical thinking, resilience, or ethical judgment, within and beyond AI-intensive job roles. Using a dataset of nearly 30 million job postings from the US, the UK and Australia, between 2018 and 2024, we distinguish between internal effects (within AI roles) and external effects (in non-AI roles) across companies, industries, and regions. This paper has three main findings. First, we find that AI-intensive roles are significantly more likely to require complementary non-technical capabilities, such as analytical thinking, resilience, and digital literacy. Second, these complementary skills are associated with meaningful wage premiums, particularly in managerial, sales or finance roles working with AI. Third, we show that AI diffusion has potential spillover effects: as AI adoption rises within companies, industries, and regions, demand for complementary skills increases even in non-AI roles while demand for substitutable skills - summarisation, translation or customer service - decreases. These trends hold across geographies, including the United States, United Kingdom, and Australia, confirming the robustness of our findings. Together, these findings indicate that AI is not simply replacing tasks or requiring more AI developer skills; it may be transforming workforce skill requirements to favor human attributes that enhance collaboration with intelligent systems.