arXiv:2605.18474v2 Announce Type: replace
Abstract: The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing LLM fingerprinting methods, particularly active approaches that embed identity signals via fine-tuning, achieve high accuracy and robustness, they suffer from significant scalability bottlenecks. These methods typically treat fingerprint injection as an independent, one-off optimization task rather than a reusable capability, necessitating separate, resource-intensive training for every new identity. This incurs prohibitive computational costs and deployment delays. To address this, we propose Prompt2Fingerprint (P2F), the first framework that reformulates fingerprinting as a conditional parameter generation task. By leveraging a specialized generator, P2F maps textual descriptions directly to low-rank parameter increments in a single forward pass, enabling plug-and-play LLM fingerprint injection without further model retraining. Our experiments demonstrate that P2F maintains high fingerprint accuracy, harmlessness, and robustness while significantly reducing computational overhead, offering a scalable and instant solution for LLM ownership management.
Science Journals
arXiv:2502.04575v3 Announce Type: replace-cross
Abstract: Given an unnormalized probability density $\pi\propto\mathrm{e}^{-V}$, estimating its normalizing constant $Z=\int_{\mathbb{R}^d}\mathrm{e}^{-V(x)}\mathrm{d}x$ or free energy $F=-\log Z$ is a crucial problem in Bayesian statistics, statistical mechanics, and machine learning. It is challenging especially in high dimensions or when $\pi$ is multimodal. To mitigate the high variance of conventional importance sampling estimators, annealing-based methods such as Jarzynski equality and annealed importance sampling are commonly adopted, yet their quantitative complexity guarantees remain largely unexplored. We take a first step toward a non-asymptotic analysis of annealed importance sampling. In particular, we derive an oracle complexity of $\widetilde{O}\left(\frac{d\beta^2{\mathcal{A}}^2}{\varepsilon^4}\right)$ for estimating $Z$ within $\varepsilon$ relative error with high probability, where $\beta$ is the smoothness of $V$ and $\mathcal{A}$ denotes the action of a curve of probability measures interpolating $\pi$ and a tractable reference distribution. Our analysis, leveraging Girsanov's theorem and optimal transport, does not explicitly require isoperimetric assumptions on the target distribution. Finally, to tackle the large action of the widely used geometric interpolation, we propose a new algorithm based on reverse diffusion samplers, establish a framework for analyzing its complexity, and empirically demonstrate its efficiency in tackling multimodality.
arXiv:2507.06428v2 Announce Type: replace-cross
Abstract: We mathematically analyze and numerically study an actor-critic machine learning algorithm for solving high-dimensional Hamilton-Jacobi-Bellman (HJB) partial differential equations from stochastic control theory. The architecture of the critic (the estimator for the value function) is structured so that the boundary condition is always perfectly satisfied (rather than being included in the training loss) and utilizes a biased gradient which reduces computational cost. The actor (the estimator for the optimal control) is trained by minimizing the integral of the Hamiltonian over the domain, where the Hamiltonian is estimated using the critic. We show that the training dynamics of the actor and critic neural networks converge in a Sobolev-type space to a certain infinite-dimensional ordinary differential equation (ODE) as the number of hidden units in the actor and critic $\rightarrow \infty$. Further, under a convexity-like assumption on the Hamiltonian, we prove that any fixed point of this limit ODE is a solution of the original stochastic control problem. This provides an important guarantee for the algorithm's performance in light of the fact that finite-width neural networks may only converge to a local minimizers (and not optimal solutions) due to the non-convexity of their loss functions. In our numerical studies, we demonstrate that the algorithm can solve stochastic control problems accurately in up to 200 dimensions. In particular, we construct a series of increasingly complex stochastic control problems with known analytic solutions and study the algorithm's numerical performance on them. These problems range from a linear-quadratic regulator equation to highly challenging equations with non-convex Hamiltonians, allowing us to identify and analyze the strengths and limitations of this neural actor-critic method for solving HJB equations.
arXiv:2509.15022v3 Announce Type: replace-cross
Abstract: Accelerating materials development requires quantitative linkages between processing, microstructure, and properties. In this work, we introduce a framework for mapping microstructure onto a low-dimensional material manifold that is parametrized by processing conditions. A key innovation is treating microstructure as a stochastic process, defined as a distribution of microstructural instances rather than a single image, enabling the extraction of material state descriptors that capture the essential process-dependent features. We leverage the manifold hypothesis to assert that microstructural outcomes lie on a low-dimensional latent space controlled by only a few parameters. Using phase-field simulations of spinodal decomposition as a model material system, we compare multiple microstructure descriptors (two-point statistics, chord-length distributions, and persistent homology) in terms of two criteria: (1) intrinsic dimensionality of the latent space, and (2) invertibility of the processing-to-structure mapping. The results demonstrate that distribution-based descriptors can recover a two-dimensional latent structure aligned with the true processing parameters, yielding an invertible and physically interpretable mapping between processing and microstructure. In contrast, descriptors that do not account for microstructure variability either overestimate dimensionality or lose predictive fidelity. The constructed material manifold is shown to be locally continuous, wherein small changes in process variables correspond to smooth changes in microstructure descriptors. This data-driven manifold mapping approach provides a quantitative foundation for microstructure-informed process design and paves the way toward closed-loop optimization of processing--structure--property relationships in an integrated materials engineering context.
arXiv:2602.09061v2 Announce Type: replace-cross
Abstract: Arnold Zellner published a seminal paper on Bayes' theorem as an optimal information processing rule, a result that led to the variational formulation of Bayes' theorem, and a central idea in generalized variational inference. Almost 40 years later, we revisit these ideas, but from the perspective of information deletion. We investigate rules that update a posterior distribution into an antedata distribution when a portion of data is removed. In such context, a rule that does not destroy or create nonexistent information is called the optimal information deletion rule and we prove that it coincides with the leave-data-out posterior from Bayes' theorem.
arXiv:2603.07018v2 Announce Type: replace-cross
Abstract: Treatment effects estimated from a randomized controlled trial are local not only to the study population but also to the time at which the trial was conducted. The literature on generalizing experimental findings to new populations is extensive, yet transporting effects across time has received far less attention, and even defining the target estimand is nonobvious. We formalize the transported average treatment effect under a separable temporal effects assumption, derive two identification strategies: replicated trials and common arm, and develop doubly robust, semiparametrically efficient estimators for each. Applied to a large archive of headline A/B tests, the common arm strategy is substantially more precise but exhibits systematic bias when the temporal factor depends on the gap between intervention and measurement rather than on measurement time alone, while the replicated trials strategy, which allows this dependence, tracks the ground truth more faithfully. Simulation studies investigate when each strategy is reliable and when it silently fails.
arXiv:2503.16309v2 Announce Type: replace-cross
Abstract: Advanced navigation techniques in image-guided interventions and surgical robotics require the rapid and precise alignment of 3D preoperative volumes (e.g., CT, MRI) to 2D intraoperative images (e.g., X-ray fluoroscopy). However, existing 2D/3D registration methods fail to generalize across the broad spectrum of fluoroscopy-guided procedures: traditional intensity-based optimizers require careful hyperparameter tuning for each subject, while deep learning approaches demand extensive manually labeled datasets and remain constrained to the specific anatomy on which they were trained. To address these limitations, we present xvr, a self-supervised framework that combines patient-specific neural networks with gradient-based optimization for automatic 2D/3D registration. xvr leverages physics-based simulation to generate training data from a patient's own preoperative scan, eliminating the need for manual annotation. We present a foundation model pretrained on thousands of whole-body scans, achieving patient-specific adaptation for any anatomical region in only 5 minutes of finetuning. In the largest evaluation of 2D/3D registration on real fluoroscopy to date, xvr achieves high accuracy in seconds across diverse anatomical structures, imaging modalities, and hospitals, improving upon the accuracy of existing methods by an order of magnitude. xvr makes pan-anatomical 2D/3D rigid registration accessible to broad clinical and research communities through open-source software at https://xvr.csail.mit.edu.
arXiv:2605.05190v2 Announce Type: replace-cross
Abstract: Electro-optic modulation is central to classical optical communications and emerging quantum technologies. High-confinement optomechanical crystal modulators enable microwave-optical transduction through strong optomechanical interactions and offer a promising interface between superconducting qubits and optical fibers. However, their performance is limited by thermal noise from optical absorption. Release-free optomechanical crystals provide improved thermal anchoring but have not yet been integrated into a microwave-optical transducer. Here, we demonstrate a release-free electro-optomechanical transducer combining strong optomechanical interactions in silicon with the efficient piezoelectricity of lithium niobate via micro-transfer printing. We observe electro- and optomechanical coupling rates compatible with quantum-level operation when co-integrated with a superconducting microwave circuit. This advance moves release-free electro-optomechanical devices toward practical microwave-optical interfaces.
arXiv:2605.11597v2 Announce Type: replace-cross
Abstract: The geometry of Bloch bands affects many physical properties of crystalline solids and other spatially periodic systems. Direct experimental determination of such geometry is an active area of research. In this work, we focus on the fundamental connection between optical excitations and the relative geometry of pairs of Bloch bands, as characterized by the interband Berry connection. We simulate the response of electrons in solids to optical excitation by the response of ultracold fermionic atoms in optical lattices to periodic modulation of the lattice position. The strength of resonant excitation between bands, measured at each quasimomentum and for various lattice-shaking polarizations, directly maps out the interband Berry connection. We apply this method to the optical honeycomb lattice, driving excitations between the ground $n=1$ band and the excited $n'=\{2,3,4\}$ bands. We observe transparency lines of quasimomenta at which the response to excitation of specific polarization is zero. Further, the interband Berry connection between bands 1 and 3 shows irreducible Dirac strings connecting the $K$ and $K'$ points in the Brillouin zone, lines along which the interband Berry connection abruptly changes orientation. Our work establishes optical response as a powerful tool for characterizing geometrical and topological properties of band structure.
arXiv:2605.19603v1 Announce Type: cross
Abstract: Understanding the relationship between morphology and performance in organic solar cells is essential for developing devices that are both high performing and resilient to aging. This work introduces a unique method capable of calculating the current-voltage (JV) curve of complex heterojunction morphologies containing up to five phases (donor amorphous, donor crystalline, acceptor amorphous, acceptor crystalline, mixed amorphous) with a very low computation time using morphology-aware descriptors of light absorption, exciton dissociation, non-geminate recombination and free charge carrier mobilities. The method is validated against Monte Carlo and 3D drift-diffusion simulations and applied to P3HT:PCBM and PM6:Y6 systems, shedding light on the physical compromises encountered to optimize device performance and lifetime. Finally, we show that the morphology-performance relationship is dependent on the materials system studied.
arXiv:2605.20158v1 Announce Type: new
Abstract: Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explanations actually reflect the visual evidence underlying the model's decision is largely unverified, since ground-truth annotations for internal model reasoning are typically unavailable. We address this question for chest X-ray (CXR) reasoning by developing a causal evaluation framework that retains only CXR-VQA samples for which the expert-annotated region is verified, via counterfactual editing, to be causally responsible for the model's prediction. Using this framework across 11 attribution methods, six open-source LVLMs, and two output modes (direct answer and step-by-step reasoning), we find that existing attribution methods often fail to identify the evidence used by LVLMs. To address this failure, we propose MedFocus, a concept-based attribution method that localizes clinically meaningful anatomical regions via unbalanced optimal transport and measures their causal effect on model outputs through targeted interventions. MedFocus produces spatial, concept-level, and token-level attributions and substantially outperforms prior methods, taking a step toward more trustworthy attribution for medical LVLMs. Our data and code are available at https://github.com/gzxiong/medfocus/.
arXiv:2605.20123v1 Announce Type: new
Abstract: The growing adoption of Retrieval-Augmented Generation (RAG) has led to a rise in adversarial attacks. Existing defenses, relying on semantic analysis or voting, face a trade-off between high computational cost and limited robustness under strong poisoning attacks. Their fundamental limitation is the exclusive focus on semantic content relevance, while neglecting the retrieval context that is critically defined by ranking structures. To this end, we investigate the bidirectional ranking behavior of poisoned and benign documents, and discover a key discriminative pattern: poisoned documents exhibit significantly stronger alignment between their backward rankings and the query's forward ranking. Capitalizing on this, we propose BiRD, a bidirectional ranking defense mechanism built upon a dual-signal framework that leverages forward ranking to assess semantic content relevance and backward ranking to quantify ranking context consistency. This design directly addresses the fundamental limitation of prior approaches, enabling simultaneous efficiency and robustness. Extensive evaluation across 3 datasets with 3 retrievers and 3 LLMs under 2 attack scenarios validates BiRD's effectiveness. Notably, BiRD reduces the attack success rate of PoisonedRAG by up to 54% while simultaneously improving task accuracy by up to 56%, with average additional latency under 1 second.
arXiv:2605.20107v1 Announce Type: new
Abstract: JEPAs often regularize one-view embeddings toward an isotropic Gaussian, implicitly baking Euclidean symmetry into the representation. We show that this is not merely a benign default. For a known structured downstream geometry $H\succ0$, the minimax and maximum-entropy covariance under a Hamiltonian energy budget is $(c/d)H^{-1}$, and Euclidean isotropy incurs a closed-form price of isotropy. More importantly, when the downstream geometry is unknown, no geometry-independent fixed marginal target is canonical: every fixed covariance shape can be maximally misaligned for some structured geometry. We further show that even oracle one-view marginals do not identify the JEPA view-to-view predictive coupling. These results suggest that the structural bias in JEPAs should enter the cross-view coupling rather than a fixed encoder marginal. We instantiate this principle with \textbf{HamJEPA}, which encodes each view as a phase-space state $(q,p)$ and predicts view-to-view transitions with a learned Hamiltonian leapfrog map, while non-isotropic scale and spectral floors prevent collapse. In a deliberately headless token protocol, HamJEPA improves over SIGReg on CIFAR-100 by $+4.89$ kNN@20 and $+3.52$ linear-probe points at 30 epochs, and by $+6.45$ kNN@20 and $+10.64$ linear-probe points at 80 epochs, while a matched MLP predictor ablation shows that the symplectic coupling is the ingredient driving the neighborhood-geometry gain. On ImageNet-100, HamJEPA-$q$ improves by $+4.82$ kNN@20 and $+7.52$ linear-probe points at 45 epochs.
arXiv:2605.19660v1 Announce Type: new
Abstract: The rapid advancement toward long-context reasoning and multi-modal intelligence has made the memory footprint of the Key-Value (KV) cache a dominant memory bottleneck for efficient deployment. While the established per-channel quantization effectively accommodates intrinsic channel-wise outliers in Key tensors, its efficacy diminishes under extreme compression. In this work, we revisit the inherent limitations of the per-channel quantization paradigm from both empirical and theoretical perspectives. Our analysis identifies Token Norm Imbalance (TNI) as the primary bottleneck to quantization fidelity. We demonstrate that TNI systematically amplifies errors when shared quantization parameters are required to span token groups exhibiting substantial norm disparities. Instead of relying on intricate quantization pipelines (e.g., TurboQuant), we propose OScaR (Omni-Scaled Canalized Rotation), an accurate and lightweight KV cache compression framework for X-LLMs (i.e., text-only, multi-modal, and omni-modal LLMs). Advancing the per-channel paradigm, OScaR employs Canalized Rotation followed by Omni-Token Scaling to mitigate TNI-induced sequence-dimensional variance both effectively and efficiently, further supported by our optimized system design and CUDA kernels. Extensive evaluations across X-LLMs show that OScaR consistently outperforms existing methods and achieves near-lossless performance under INT2 quantization, establishing it as a robust, low-complexity, and universal framework that defines a new Pareto front. Compared with the BF16 FlashDecoding-v2 baseline, our OScaR implementation achieves a notable up to 3.0x speedup in decoding, reduces memory footprint by 5.3x, and increases throughput by 4.1x. The code for OScaR is publicly available at https://github.com/ZunhaiSu/OScaR-KV-Quant.
arXiv:2605.19307v1 Announce Type: new
Abstract: Visual Question Answering (VQA), as the representative multimodal task, serves as a key benchmark for evaluating the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, existing evaluations largely rely on static datasets and accuracy-based metrics, which fail to capture robustness, consistency, and generalization. Inspired by Metamorphic Testing (MT), we propose Metamorphic Robustness Assessment (MetaRA), a testing framework that employs Metamorphic Relations (MRs) to systematically probe vulnerabilities in MLLM-based VQA systems. MetaRA generates controlled variations of image-question inputs based on specific MRs and evaluates models across diverse conditions. Applying MetaRA to multiple MLLM-based VQA models across different tasks reveals nuanced failure patterns, including sensitivity to linguistic perturbations, over-reliance on superficial visual cues, and deeper weaknesses in multimodal reasoning. Experimental results demonstrate that MetaRA provides richer diagnostic insights than conventional accuracy metrics, exposing failure modes that remain hidden under standard benchmarks. Overall, this work highlights the need for systematic robustness evaluation in VQA and positions metamorphic assessment as a scalable, model-agnostic approach toward trustworthy multimodal AI.
arXiv:2605.19223v1 Announce Type: new
Abstract: While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over complex narratives remains poorly evaluated. Existing summarization benchmarks fragment supervision across isolated granularities, such as keyframes, key shots, or disjointed text summaries, failing to capture the inherently hierarchical structure of cross-modal alignment. To address this critical gap, we introduce HAVEN, a hierarchically aligned multimodal benchmark for unified video understanding. HAVEN pioneers a fully granular (frame, shot, and video levels) and fully multimodal (video and text) dataset architecture, complete with explicit, continuous alignment between modalities. Built upon this unified annotation paradigm, we propose a comprehensive evaluation suite spanning summarization, temporal reasoning, multimodal grounding, and saliency ranking. Extensive benchmarking of state-of-the-art MLLMs exposes a persistent gap between surface-level textual fluency and grounded multimodal understanding. Ultimately, HAVEN advances the evaluation of multimodal systems beyond traditional QA formats, offering a rigorous, standardized testbed to drive future research in interpretable, hierarchical video understanding. We publicly release the dataset, benchmark suite, and evaluation protocols.
arXiv:2605.19220v1 Announce Type: new
Abstract: Uncertainty Quantification (UQ) is widely regarded as the primary safeguard for deploying Large Language Models (LLMs) in high-stakes domains. However, we argue that the field suffers from a category error: mainstream UQ methods for LLMs are just unsupervised clustering algorithms. We demonstrate that most current approaches inherently quantify the internal consistency of the model's generations rather than their external correctness. Consequently, current methods are fundamentally blind to factual reality and fail to detect ``confident hallucinations,'' where models exhibit high confidence in stable but incorrect answers. Therefore, the current UQ methods may create a deceptive sense of safety when deploying the models with uncertainty. In detail, we identify three critical pathologies resulting from this dependence on internal state: a hyperparameter sensitivity crisis that renders deployment unsafe, an internal evaluation cycle that conflates stability with truth, and a fundamental lack of ground truth that forces reliance on unstable proxy metrics to evaluate uncertainty. To resolve this impasse, we advocate for a paradigm shift to UQ and outline a roadmap for the research community to adopt better evaluation metrics and settings, implement mechanism changes for native uncertainty, and anchor verification in objective truth, ensuring that model confidence serves as a reliable proxy for reality.
arXiv:2605.19161v1 Announce Type: new
Abstract: As AI-generated problem sets gain traction in introductory physics courses, their technical correctness is well established - but the social assumptions embedded in their framing have gone largely unexamined. This study analyzes 600 introductory physics problems generated by four AI systems - Grok~4, GPT-5.2, Claude Sonnet 4.6, and Gemini 3 Flash - across structured prompts involving occupations (CEO, Physicist, High School Teacher, Nurse, Construction Worker, and Migrant Worker). Problems were coded on five dimensions: hazard presence, hazard type, agency role, cognitive role, and object ownership. While the physics content is technically sound across all platforms, our analysis reveals systematic occupational stratification in narrative framing. Hazardous scenarios were concentrated in Migrant Worker and Construction Worker problems, with exposure-related hazards (electrocution, burns, radiation, heat or chemical exposure) especially concentrated in Migrant Worker problems. Passive-accident framing - the persona as the recipient of an injury - appeared in one in eight Migrant Worker problems and never appeared for the Physicist, Teacher, or CEO. Possessive ownership language was reserved almost exclusively for the CEO. These patterns suggest that AI-generated physics problems can introduce surface-level diversity while reproducing occupational hierarchies in who acts, who owns, and who is placed at risk. We discuss implications for physics teaching and offer simple screening strategies for instructors using AI-generated problems.
arXiv:2605.19351v1 Announce Type: new
Abstract: Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required, such as fire evacuation or authority-supervised emergency, remains poorly characterized. We propose PAVE (Perception, Assessment, Verdict, Emulation), a novel four-module cognitive architecture that addresses this gap end to end: (i) Perception extracts a structured context with explicit authority distance, peer behaviors, and severity-tagged situational cues; (ii) Assessment scores the context along five scalars including an explicit legitimacy judgment that checks necessity, proportionality, and absence of alternatives; (iii) Verdict decides to comply or violate under a hard legitimacy gate, with a per-agent threshold elicited from the persona; (iv) Emulation enacts the verdict and scopes the violation to the rule the trigger justifies. We instantiate PAVE in Voville, a tile-based traffic environment forked from Smallville, and evaluate across three scenarios, four LLM backbones, and a focused ablation. PAVE agents satisfy four properties simultaneously: legitimate violation (only when a trigger justifies it), authority deference (officer instructions override even high legitimacy), bounded scope (violations confined to the targeted rule), and recovery (baseline restored once the trigger ends). PAVE agents make more structured and interpretable decisions than vanilla across all four properties, and human evaluators rate them as more plausible. Ablating the legitimacy gate reproduces vanilla-like failures. We release Voville, the PAVE prompts and code, and the evaluation pipeline.
arXiv:2605.19431v1 Announce Type: new
Abstract: Multirotor aerial robots excel at maneuvering in three-dimensional space, and recent advances enable nimble navigation in cluttered and confined environments, especially for small airframes. By contrast, platforms built for high-altitude work tend to be larger to deliver high thrust for stable physical interaction with the environment. However, these conflicting design requirements create a long-standing trade-off between nimble navigation and robust aerial manipulation. Here, we present LEGION units, which are reconfigurable modular aerial robots capable of in-flight self-assembly for cooperative manipulation, drawing inspiration from the self-organized collectives formed by ants. Each unit retains nimble maneuverability while joint-equipped docking interfaces at both ends enable end-to-end self-assembly into a flying manipulator. We show that multiple units autonomously dock in flight; once latched, they maintain a zero-clearance interlock by controlling the contact force and torque, enabling reliable aggregation and articulated motion even outdoors. We further show that self-reconfigurability enables morphological switching between nimble individual flight and collective articulated manipulation, while realizing core in-flight manipulation primitives including pushing, pulling, rotating, grasping, and carrying. LEGION's self-organization enables aerial robots, especially in swarms, to shift from passive observers to active participants in their environment, broadening the scope of aerial physical interaction.
arXiv:2605.19554v1 Announce Type: new
Abstract: Instilling creativity in text-to-image (T2I) generation presents a significant challenge, as it requires synthesized images to exhibit not only visual novelty and surprise, but also artistic value. Current T2I models, however, are largely optimized for literal text-image alignment with their data distribution, and their noise prediction networks constrain the generation to high-probability regions, consequently generating outputs that lack authentic creativity. To address this, we propose a Self-Creative Diffusion (SCDiff) model for meaningful T2I generations featuring two core modules: a learnable spatial weighting (LSW) module and a visual-semantic mixing loss (VSML). The LSW module designs a parametric Kaiser-Bessel window to reinforce central image features, fostering novel and surprising generation. The VSML module introduces a dual loss function: a similarity loss constrains that the new images align with its textual description, while a diversity loss maximizes its distinction from the original image, enhancing both semantic value and visual novelty. Extensive experiments demonstrate that our model substantially improves creativity, semantic alignment, and visual coherence, offering a simple yet powerful framework for generating creative objects.
arXiv:2605.00856v3 Announce Type: replace-cross
Abstract: Accurate and continuous estimation of cognitive workload is fundamental to creating adaptive human-machine systems. However, designing architectures that balance representational capacity with computational efficiency has been challenging for practical deployment. This paper introduces 1BT, a One-Block Transformer for compact and efficient EEG-based cognitive workload assessment. The model aggregates multi-channel temporal sequences via a minimal latent bottleneck, using a single cross-attention module followed by lightweight self-attention. A controlled study involving 11 participants performing three cognitively diverse tasks (abstract reasoning, numerical problem-solving, and an interactive video game) was conducted with continuous EEG recordings across two workload levels. Systematic architectural analysis identifies the most compact configuration that preserves high performance, while substantially lowering computational cost. The final model achieves high workload classification performance with under 0.5 million parameters and 0.02 GFLOPs, paving the way for a design direction for real-time cognitive workload monitoring in resource-constrained settings.
arXiv:2604.02064v3 Announce Type: replace-cross
Abstract: We provide here a universal approximation theorem with precise quantitative error bounds for noisy quantum neural networks. We focus on applications to Quantitative Finance, where target functions are often given as expectations. We further provide a detailed numerical analysis, testing our results on actual noisy quantum hardware.
arXiv:2512.25061v3 Announce Type: replace-cross
Abstract: Charge self-consistent DFT+DMFT quantitatively captures dynamical electronic correlations in real materials, but its cost precludes the large-scale thermodynamic sampling required for phase boundaries and equations of state. Here, we develop a physics-constrained machine-learning warm start for realistic DFT+DMFT: E(3)-equivariant graph neural networks predict a compact, real-valued representation of the local self-energy and Fermi level -- \{\,$\Sigma(\infty),\,\Sigma_\ell,\,E_f\,$\} -- tied to the known high-frequency and analytic structure of $\Sigma(i\omega_n)$, and used to initialize the full DFT+DMFT self-consistency cycle. Across metallic Fe, correlated FeO, and Mott-insulating NiO, the scheme yields a 2--4 times reduction in the number of DMFT iterations required to reach self-consistency. As a demanding application, we leverage this capability to generate correlated energies and forces for Fe at core pressures, train an equivariant machine-learned interatomic potential, and determine the hcp-Fe melting curve by solid--liquid coexistence simulations in the NVE ensemble in 9216-atom cells. We obtain a melting temperature of 6225 K at 330 GPa, in agreement with recent experimental constraints and consistent with the view that dynamical electronic correlations contribute to the discrepancy between DFT-based predictions and experiment.
arXiv:2603.14918v2 Announce Type: replace-cross
Abstract: Model-based approaches for (bio)process systems often suffer from incomplete knowledge of the underlying physical, chemical, or biological laws. Universal differential equations, which embed neural networks within differential equations, have emerged as powerful tools to learn this missing physics from experimental data. However, neural networks are inherently opaque, motivating their post-processing via symbolic regression to obtain interpretable mathematical expressions. Genetic algorithm-based symbolic regression is a popular approach for this post-processing step, but provides only point estimates and cannot quantify the confidence we should place in a discovered equation. We address this limitation by applying Bayesian symbolic regression, which uses Reversible Jump Markov Chain Monte Carlo to sample from the posterior distribution over symbolic expression trees. This approach naturally quantifies uncertainty in the recovered model structure. We demonstrate the methodology on a Lotka-Volterra predator-prey system and then show how a well-designed experiment leads to lower uncertainty in a fed-batch bioreactor case study.