arXiv:2607.15047v1 Announce Type: new
Abstract: Mild Cognitive Impairment is a critical early stage of cognitive decline that frequently precedes Alzheimer's disease, yet its automated detection from neuropsychological drawing tests remains fundamentally constrained by data scarcity, class imbalance, and diagnostic ambiguity near clinical boundaries. Existing methodologies attempt to bypass these constraints using computationally expensive, fully fine-tuned hybrid architectures that relegate spatial explainability to a post-hoc approximation rather than an intrinsic model property. We propose a parameter-efficient framework utilizing frozen DINOv2-Small model adapted via three modality-specific learnable prompt tokens while Operating with 1.19 million trainable parameters, each token serves as a query in a shared cross-attention layer over the source image patch tokens. Crucially, spatial explainability is achieved directly through these attention maps; as a structural consequence of the architecture. Then task-conditioned embeddings fused via an attention module to quantify modality-level importance per subject. To handle boundary ambiguity, a MoCA-adapted focal loss introduced that integrates continuous cognitive scores into the training target, loss modulation, and adaptive sample weighting, strictly generalizing standard soft-label approaches. Under stratified five-fold cross-validation, the proposed architecture yields an MCI-class F1 of 0.641 and an AUC of 0.795, outperforming the computationally heavier ResViT baseline by 0.110 in MCI-class F1.
Science Journals
arXiv:2607.15059v1 Announce Type: new
Abstract: The Matilda effect describes the systematic under-recognition of women's scientific contributions. We investigated its historical evolution by analyzing over 220 million publications (1900-2025) from OpenAlex, inferring the gender of roughly 60 million authors. To quantify this under-recognition, we calculated the ratio between the overall share of female authors and female corresponding authors. Because corresponding authorship denotes intellectual leadership and primary academic credit, systematic exclusion from this role directly measures the Matilda effect. Our analysis reveals that overall female participation rose from approximately 10% in the 1910s to over 40% recently. For most of the 20th century, women were disproportionately excluded from corresponding authorship, confirming a historical Matilda effect. However, this trend inverted over the past two decades, indicating a global decline. Despite this overall progress, distinct disparities persist: the physical sciences and Asian countries lag behind, whereas the health sciences and Latin America approach gender parity.
arXiv:2607.15048v1 Announce Type: new
Abstract: Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation, lane-level perception, and automatic road annotation. Recent mesh-based road surface reconstruction methods have shown promising results, but they still suffer from limited reconstruction quality and high optimization cost, especially in large-scale driving scenarios. To address these limitations, we propose ROADGS-T, a robust and efficient large-scale road surface mapping framework based on adaptive meshgrid Gaussian representation. Specifically, we model the road surface by placing 2D Gaussian surfels on a meshgrid, where each surfel explicitly stores color, semantic, and geometric information. Compared with conventional mesh-based representations and 3D Gaussian primitives, the proposed meshgrid Gaussian representation better matches the thin-surface property of roads while significantly reducing redundant primitives and overlap during optimization. To further improve representation efficiency and structural fidelity, we introduce a road-structure-aware adaptive meshgrid strategy, which allocates denser Gaussian surfels to geometrically or semantically complex regions, such as lane markings, road boundaries, and height discontinuities, while maintaining a compact representation in flat road areas. Moreover, instead of relying on a single nearest vehicle pose, we design a trajectory-consistency-guided pose-robust refinement strategy, which estimates local surface priors from multiple neighboring poses and adaptively weights pose-guided height regularization according to their geometric consistency.
arXiv:2607.15049v1 Announce Type: new
Abstract: Characterizing the mechanical response of materials traditionally requires solving optimization problems in which model parameters are calibrated or trained to minimize the discrepancy between model predictions and experimental data. This process can be computationally expensive and time-consuming. To overcome this limitation, we propose two neural operator architectures that directly map experimentally measured data to the constitutive functions governing the mechanical response of the material: Physics-Augmented Neural Operators (PANO) and Constitutive Artificial Neural Operators (CANO). The proposed neural operators approximate the mapping between the infinite-dimensional input space of full-field displacement measurements and net reaction forces, and the infinite-dimensional output space of hyperelastic strain-energy density functions. The displacement fields are encoded through Laplacian eigenfunctions to obtain discretization-independent and noise-robust predictions. Our framework constrains the output space to physically admissible material models that satisfy fundamental physical requirements by design. The neural operators are trained on simulated data tuples of displacement fields and reaction forces for a range of material models. Once trained, the neural operators enable near-instantaneous material characterization and require only a single forward pass to infer the strain-energy density function from a given experimental dataset. We test the predictive power of the neural operators for unseen data, noisy data, data with missing information, data from different spatial discretizations, and data from geometries of different sizes.
SCITUS: A Multi-Jurisdictional Framework for Adapting NIST AI RMF to the Canadian Regulatory Context
arXiv:2607.15051v1 Announce Type: new
Abstract: Canadian organizations deploying artificial intelligence systems face a fragmented regulatory landscape spanning federal requirements (the Treasury Board Directive on Automated Decision-Making) and divergent provincial regulations across Ontario, Quebec, Alberta, Manitoba, and British Columbia. The death of Bill C-27 (Artificial Intelligence and Data Act) in January 2025 - and the federal government's June 2026 confirmation that it will pursue targeted instruments rather than omnibus AI legislation - leaves organizations without unified compliance guidance. Global frameworks such as NIST AI RMF 1.0, the EU AI Act, and ISO/IEC 42001 provide valuable guidance but lack systematic methodologies for adaptation to multi-jurisdictional national contexts. We present SCITUS (Systematic Canadian Integration for Trustworthy and Unified Standards), a comprehensive framework adapting NIST AI RMF 1.0 to Canadian federal and provincial AI regulations simultaneously. SCITUS integrates seven trustworthy-AI characteristics enhanced for Canadian requirements, four core governance functions, a novel multi-jurisdictional compliance mapping methodology, and a versioned control catalog that has evolved from 31 controls (v1.0, June 2025) to 57 controls (v2.0, July 2026) in response to regulatory developments - including Canada's first regulatory findings on generative-AI training data - and the documented 2026 agentic-AI threat landscape. We demonstrate applicability through scenarios spanning federal government, provincial healthcare, and the private sector, and argue that systematic adaptation of NIST AI RMF to multi-jurisdictional requirements offers significant advantages over jurisdiction-by-jurisdiction compliance and provides a replicable model for other federal systems.
arXiv:2607.15052v1 Announce Type: new
Abstract: Federated Learning (FL) enables collaborative model training while preserving privacy by keeping data local. However, the risk of sensitive data leakage through model updates necessitates the use of secure aggregation protocols. Existing server-based secure aggregation protocols typically require the server to forward sensitive data shared between users, which increases communication overhead and introduces potential security risks. In this work, we propose a novel secure aggregation protocol based on two-layer secret sharing to address these issues. By combining Shamir's Secret Sharing with 2-out-of-2 additive secret sharing using a Pseudo-Random Function (PRF), our protocol eliminates direct communication between users, thereby removing the need for the server to forward data. We further extend the protocol with Key-homomorphic PRF (KhPRF) to support high-dimensional data aggregation and apply it to FL, enabling one-shot secure aggregation with a single server and no intermediary data forwarding. To reduce user overhead, we design a new encoding method based on the Chinese Remainder Theorem for the almost KhPRF-based mask, reducing the number of KhPRF calls and mitigating the model update expansion issue after masking. Experimental results show that our scheme significantly outperforms existing methods in terms of auxiliary node overhead. For instance, when the number of users is 100, our scheme improves communication efficiency by nearly 100 times and reduces computational overhead by approximately 17\%. Moreover, user computation time can be reduced by 51\% to 75\% when the input length is $2^{18}$.
arXiv:2607.15053v1 Announce Type: new
Abstract: The Internet taught us that the value of a network depends on \emph{how} its nodes connect: broadcast stars scale as $V\!\propto\!N$ (Sarnoff), fully-connected meshes as $N^2$ (Metcalfe), and group-forming networks as $2^{N}$ (Reed). We ask the analogous question for networks of AI agents. We model the net value of connection as a function of coordination-group size, derive from it the properties an optimal collaboration protocol must have, and introduce ANet Patu-1 -- a self-organizing consensus protocol in which the network continuously re-forms its own coalitions, adaptively riding the upper envelope of all three regimes at $O(1)$ parallel consensus rounds. To measure value without opinion-grading, we score an emergent protocol by formally specifying it and deriving its complexity, the way distributed algorithms are analyzed. Two results follow. (i)~Emergence -- a crowd of the \emph{cheapest} model, when heterogeneous, starts weak but its collective value compounds with $N$ and \emph{overtakes} a crowd of a far \emph{stronger} model that is homogeneous: a crossover that marks a scaling law for collaboration rather than for scale. (ii)~Reflexivity -- a heterogeneous network, given only its own problem and no design hints, converges on ANet Patu-1 itself, reconstructing the high-dimensional law that governs its own connective value.
arXiv:2607.15054v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated substantial promise in spatial understanding. Existing works typically incorporate prior knowledge extracted from a pre-trained foundation model to further enhance the spatial awareness of MLLMs. In this paper, we first reveal that when integrating diverse foundation models into MLLMs, different models provide complementary spatial priors that benefit different tasks. Motivated by this, we propose $\textbf{ViPS}$, a novel multi-model prior framework designed to fully unleash the potential of incorporating multiple $\textbf{Vi}$sual $\textbf{P}$riors from diverse models into MLLMs for $\textbf{S}$patial understanding. Specifically, ViPS introduces an Efficient Prior Proxy to generate multiple foundational priors with minimal inference overhead, and a Dynamic Prior Fusion mechanism to achieve harmonious and context-aware prior fusion and injection from the prior proxies. Extensive experiments demonstrate that ViPS successfully harmonizes diverse visual priors, establishing new state-of-the-art performance across multiple complex spatial reasoning and 3D spatial understanding benchmarks. Project page: https://visual-ai.github.io/vips
arXiv:2607.15058v1 Announce Type: new
Abstract: CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models, yet typically their correspondences are appearance-driven and degrade under occlusion or sim-to-real domain shift. To address these limitations, we introduce SUFLECA (Scaling Up Feature LEarning for CAD Alignment), a weakly-supervised framework for zero-shot CAD alignment with two key contributions. First, SUFLECA scales up geometry-grounded feature learning from pretrained visual representations through Normalized Object Coordinates (NOCs) supervision on 674K images spanning 12 real and synthetic datasets, learning compact geometry-aware features that generalize across domains. Second, we propose a geometrically consistent matching algorithm that establishes reliable one-to-one CAD-to-image correspondences. Together, these contributions enable accurate, sub-second alignment per object instance without iterative pose refinement. On ScanNet25k, SUFLECA achieves 33.4%/42.3% category/instance accuracy, outperforming, with a smaller computational footprint, the strongest zero-shot baseline by 10.3/12.2 percentage points and, for the first time on this benchmark, even surpassing fully supervised methods. Code is available at: https://github.com/snt-arg/SUFLECA
arXiv:2607.15063v1 Announce Type: new
Abstract: In this paper, we propose an adaptive physics-preserving multiscale method for incompressible and immiscible two-phase flow in high-contrast porous media. The method couples a physics-preserving implicit-pressure explicit-saturation scheme (P-IMPES) with the mixed constraint energy minimizing generalized multiscale finite element method. The core algorithmic component is an adaptive update strategy for the saturation-dependent coefficient. Since the effective permeability \(\kappa_n=\lambda_t(S_w^n)K\) depends on the evolving saturation through the total mobility, we introduce an adaptive update algorithm that monitors the variation of the mobility-weighted coefficient and regenerates the multiscale spaces only when a prescribed tolerance is exceeded. A local postprocessing step is further used to recover fine-grid mass conservation. The analysis is a central part of the paper. We prove local conservation for both phases, the unbiased property of the phase formulation, and bounds preservation under a suitable CFL condition. For the advection-dominated case, we establish velocity and saturation error estimates, which clearly identify the contributions from the adaptive tolerance, the coarse mesh size, the spectral approximation, and the front-layer error. Numerical experiments on different high-contrast permeability fields confirm the physical properties of the method and show that smaller adaptive tolerances improve the saturation approximation while avoiding unnecessary updates of the multiscale spaces.
arXiv:2607.14997v1 Announce Type: new
Abstract: Language-conditioned quadrotor flight requires a policy to ground semantic goals, anticipate the visual consequences of ego-motion, and output control references that remain smooth and dynamically executable under rapidly changing first-person views. Existing aerial vision-language navigation and vision-language-action methods commonly use discrete actions, high-level waypoints, or instantaneous velocity commands, which provide limited supervision about how flight actions change future observations. We present AeroAct, an action-centered world-action model (WAM) for quadrotor navigation. To the best of our knowledge, AeroAct is the first WAM instantiated and demonstrated for real-world aerial flight. The model adapts a pretrained video diffusion Transformer to predict local trajectory-action chunks from egocentric visual history, proprioception, and language. Future first-person frames are used during training as dense consequence supervision, while deployment directly decodes actions without generating future video. To obtain aligned visual, state, language, and dynamically feasible action data, we build a DiffAero-based pipeline with complementary Isaac Lab and 3D Gaussian splatting renderers. We further introduce a low-cost handheld collection device that couples camera observations with motion estimates to recreate flight-like egocentric trajectories, and a self-guidance procedure that improves temporal consistency across overlapping trajectory chunks. Closed-loop simulation and real-world experiments show that temporal visual context improves target tracking and object-search performance, and that WAM-based policies can be executed on a physical quadrotor.
arXiv:2607.15065v1 Announce Type: new
Abstract: Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes each rollout expensive, limiting large-scale action search at inference time. We introduce DriftWorld, an action-conditioned world model based on drifting generative models. Rather than denoising iteratively at inference, DriftWorld learns an action-conditioned drift during training, allowing it to generate future frames from the current observation and a candidate action sequence in a single forward pass at 30+ fps, which is 17x faster on average than diffusion based baselines. We evaluate DriftWorld on standard vision-based robotic manipulation benchmarks, including Bridge-V2, RT-1, Language Table, Push-T, and Robomimic. By producing rollouts that are both accurate and fast, DriftWorld achieves state-of-the-art decision-making performance with far less inference time than diffusion-based world model baselines. Beyond online control, DriftWorld can also serve as an offline simulator for ranking real-world robot policies, with rollout-based scores correlating with ground truth at up to 0.99. These results show that drifting models are a strong fit for robot world modeling, where fast, high-quality imagination directly supports planning and policy evaluation.
arXiv:2607.15066v1 Announce Type: new
Abstract: Dissociative chemisorption (DC) of H$_2$ on the Cu(111) surface is a prototypical problem for understanding elements of heterogeneous catalysis [Science 326, 832 (2009)]. The challenge lies in modeling the reaction dynamics that in turn reflects a classical potential for atomic deformations, friction, and inelastic scattering. Here, I test the use of a set of range-separated hybrid (RSH) van der Waals density functionals (vdW-DFs) [JPCM 37, 211501 (2025)] on their ability to describe the classical barrier for dynamics in this H$_2$+Cu(111) DC problem. I furthermore document use of a variant for fast accurate predictions of the molecular quasi-particles (QPs), finding excellent performance across a set of small molecules that are often studied in catalysis. Finally, I suggest and implement a way to use that QP focus to identify what I consider a best-possible non-empirical (yet adsorbate specific) RSH vdW-DF version, denoted AHBR($\gamma^*$) for H$_2$ DC modeling, navigating what are partly conflicting requirements on the molecule and metal sides. I find that the AHBR($\gamma^*$) can determine the classical H$_2$+Cu(111) DC barrier height close to chemical accuracy. I suggest that DC modeling can test broader relevance of the physics underpinning these RSH vdW-DFs.
arXiv:2607.15068v1 Announce Type: new
Abstract: High-level synthesis (HLS) raises the abstraction level of FPGA accelerator design from hardware description languages to C/C++, but high-quality results still depend on schedule decisions such as pipelining, unrolling, tiling, reordering, and buffering. These decisions create a combinatorial design space, while many numerical kernels exhibit recurring computation patterns that suggest different optimization strategies. This paper presents PATTERNDSE, a lightweight pattern-guided design space exploration (DSE) framework for FPGA kernels written in Allo, a scheduling-oriented HLS programming system. PATTERNDSE maps recurring computation patterns, including elementwise maps, reductions, matrix-vector operations, matrix-matrix operations, and stencil-like updates, to compact schedule spaces. It then applies candidate schedules, validates functional correctness through LLVM execution, checks HLS C code generation, and uses a simple pattern-aware estimator to rank candidates before Vitis HLS synthesis. We evaluate PATTERNDSE on six representative kernels: vecadd, axpy, dot, matvec, gemm, and jacobi2d. Compared with an exhaustive-lite baseline, pattern-guided DSE reduces the number of HLS-evaluated candidates from 140 to 29, achieving a 4.83x overall search reduction and up to 12.0x reduction for individual kernels. Across all evaluated kernels, PATTERNDSE recovers the same best valid Vitis HLS latency as the exhaustive-lite baseline, demonstrating that computation-pattern information can prune unproductive schedule combinations while preserving high-quality HLS outcomes.
arXiv:2607.15072v1 Announce Type: new
Abstract: Total-f five-dimensional gyrokinetic simulations are essential for self-consistent studies of multi-scale, multiphysics transport in the edge region of diverted tokamak plasmas. However, conventional initialization with a local Maxwellian distribution often generates large-amplitude transients, particularly geodesic acoustic modes (GAMs). These transients are especially severe in the plasma edge because of steep profile gradients, strong radial electric fields, and high safety factors, and they increase the computational time required to reach a saturated turbulent state. To address this problem, we present a new initialization scheme for the total-f XGC code that uses a relaxed particle distribution obtained from a computationally inexpensive axisymmetric simulation. Before the distribution is transferred to the full turbulence simulation, phase-space smoothing is applied to reduce particle noise while preserving its neoclassical structure. Applications to the Cyclone Base Case and an ASDEX Upgrade I-mode discharge demonstrate substantial suppression of transient GAMs, reduced particle noise, and a significant reduction in time to solution.
arXiv:2607.15078v1 Announce Type: new
Abstract: Accurate modeling of compressible premixed flames, encompassing both deflagrations and detonations, remains a significant challenge for predictive Large Eddy Simulation (LES) due to the strong coupling between the thermochemical state and the local thermodynamic state. This work presents a manifold-based turbulent combustion model that ensures a fully consistent thermodynamic state between model and flow solver through an iterative procedure. The framework reproduces critical quantities including temperature, radical species, and source term profiles, addressing limitations of existing approaches that rely on low-Mach perturbations or tabulated ZND detonations without thermodynamic consistency. Validation is performed against one-dimensional and high-fidelity RDE-like data, demonstrating that the thermodynamically consistent model consistently outperforms existing approaches across a broad range of compressible flame regimes - including both deflagration and detonation. The results highlight the importance of fully accounting for the thermodynamic state to achieve accurate predictions. By capturing both deflagrative and detonative behavior within a single framework, the model provides a unified, versatile tool for LES of high-speed reacting flows and offers a foundation for future studies of compressible reacting flows, including applications to rotating detonation engines and other supersonic combustion systems.
arXiv:2607.15081v1 Announce Type: new
Abstract: Fine-tuning large language models (LLMs) on domain-specific datasets has become a standard paradigm for adapting LLMs to specialized applications. However, recent work has shown that even fine-tuning on benign task-specific data can substantially weaken the safety capabilities of LLMs. While existing efforts have made progress in identifying data responsible for safety degradation, they usually rely on a single mean vector computed over a specific model with its tokenizer to represent the safety direction, which limits both the effectiveness and transferability of their risk assessment measures. To address these limitations, we propose DataShield, a data assessment framework that identifies risky fine-tuning samples and response segments through consensus subspace alignment over joint safety-critical semantic spaces derived from multiple safety-aligned LLMs. Within these spaces, DataShield extracts consensus safe and unsafe subspaces using semantic spectral decomposition over safe and unsafe data representations. The risk of a data sample or segment is then estimated by measuring its relative alignment with the unsafe and safe subspaces, enabling both sample-level filtering and fine-grained segment-level masking. Compared with state-of-the-art filtering and masking baselines, DataShield reduces ASR by 14.6\% with sample filtering and 32.3\% with segment masking, while preserving downstream utility and avoiding target-model-specific risk computation.
arXiv:2607.15082v1 Announce Type: new
Abstract: Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two complementary approaches for newspaper structure understanding. First, we present a modular bottom-up pipeline that combines state-of-the-art open-source models: YOLO for layout detection, LayoutReader for reading order prediction, and a custom algorithm for article segmentation. This approach leverages existing robust components while maintaining flexibility and interpretability. Second, we introduce Tiramisu (Tiered Transformers for Hierarchical Structure Understanding), a novel end-to-end transformer-based architecture that explicitly models document hierarchy through an iterative tiered process. Tiramisu performs section and article separation, block localization, semantic categorization, and reading order prediction using highly parallelized attention mechanisms. Finally, we release Finlam La Libert\'e, a new dataset designed specifically for evaluating hierarchical information retrieval in historical newspapers. Experimental results demonstrate the effectiveness of both approaches in reconstructing complex newspaper hierarchies, with comparative analysis highlighting their respective strengths for scalable document digitization. The Tiramisu training code, including the synthetic newspaper generator, is available at https://git.litislab.fr/tiramisu/tiramisu-newspaper-articles-extractor.
arXiv:2607.15084v1 Announce Type: new
Abstract: Face recognition models represent each face as an embedding vector on the unit hypersphere by clustering embeddings of the same identity while pushing different identities apart through angular-margin losses. Because these losses act only on training identities, non-member identities may form clusters with different geometric properties. In this paper, we quantify the magnitude of this difference and what training-time factors control it. We compute four statistics based on cluster geometry across 180 face recognition models in a factorial design over IResNet backbone size, loss head, training duration, and the number of training identities, and evaluate each configuration on nine benchmarks. Our results indicate that the number of training identities has the largest effect on member/non-member separability, while backbone and loss head contribute far less, and that, on a same-domain held-out reference, the geometric membership signal decreases monotonically as more identities are added to training. We provide an analysis of cross-domain (pose, age, quality, ethnicity) non-member benchmarks and report that these inflate the apparent membership signal. Finally, we fuse all four statistics with a learned classifier to reveal additional membership information beyond the best individual statistic.
arXiv:2607.15024v1 Announce Type: new
Abstract: The least-squares splitting algorithm for the Monge-Amp\`ere equation has been used successfully in computations for several years, but a convergence theory for fully discrete splitting schemes of this type has remained unavailable. In this work, we introduce and analyze a finite element framework for smooth solutions of the Dirichlet Monge-Amp\`ere equation in two dimensions. The proposed schemes combine a discrete Hessian reconstruction with a local projection onto the determinant constraint. Under a discrete Miranda-Talenti estimate and standard approximation properties of the Hessian reconstruction, we prove local convergence of the iterative scheme and optimal-order convergence of its limit to the exact solution in an $H^2$-type norm. We verify the estimates for conforming $C^1$ schemes, including the Argyris element, and for $C^0$-interior penalty and DG schemes of degree at least three; quadratic $C^0$-interior penalty and DG schemes are also covered when $|u|_{H^3(\Omega)}$ is sufficiently small. To the best of our knowledge, these discretizations have not previously been proposed or analyzed for least-squares splitting methods. Numerical experiments confirm the theoretical convergence rates.
arXiv:2607.15041v1 Announce Type: new
Abstract: Weakly-supervised RGB-D Salient Object Detection (SOD) is explored to reduce the heavy burden of pixel-level annotations. But scribble annotations lack the structure and details of objects, resulting in inaccurate saliency maps. In this paper, we propose a novel scribble-supervised RGB-D SOD method, consisting of a Segment Anything Model (SAM)-driven pseudo annotation generation method (\emph{SAM-PAG}) and a state space interaction-based conditional diffusion model (\emph{$S^2$Diff}). Specifically, SAM-PAG is tailored to address the issue of sparse supervision information. In SAM-PAG, we adopt the advanced SAM to expand sparse scribbles to dense pixel-level pseudo annotations through the dual-branch structure and the consistency of segmentation masks. In $S^2$Diff, we adopt the diffusion model to iteratively refine the noisy saliency maps with the guidance of conditional information, generating accurate saliency maps. Naturally, the core of our $S^2$Diff lies in the acquisition of conditional features and the denoising of saliency maps. For the former, we employ a cross-modal conditional generation module to interweave cross-modal features through frequency integration and implicit-explicit state space interaction, effectively achieving global conditional features. For the latter, we employ a context injection module to mitigate noise interference and to enhance object information with the conditional context. With the close cooperation of SAM-PAG and $S^2$Diff, our method outperforms relevant scribble-supervised methods and achieves competitive performance compared to fully-supervised methods on seven datasets. The code and results of our method are available at https://github.com/Switch457/WeakS2Diff_SOD.
arXiv:2607.15086v1 Announce Type: new
Abstract: We study time-discrete parametric approximations of evolution equations in Hilbert spaces based on residual minimization. The solution is represented by a parametrized ansatz belonging to a low-dimensional nonlinear manifold, and time stepping is performed by minimizing suitably defined residuals at each step. Two natural residual formulations are considered: discretization followed by parametrization of the evolution equation, and discretization of the Dirac--Frenkel variational principle governing the parameter dynamics. A unified error analysis is developed for both approaches within the family of $\zeta$-methods. The resulting bounds separate the effects of time discretization from those of residual minimization and yield first- and second-order convergence under Lipschitz, one-sided Lipschitz, and dissipativity assumptions. For the variational formulation, additional stability conditions involving the conditioning of the parametrization map arise naturally. The framework is applied to Gaussian approximation manifolds, for which residual norms and gradients admit explicit closed-form expressions when polynomial operators are involved. This enables efficient implementation without spatial discretization. Numerical experiments for time-dependent Schr\"odinger equations illustrate the theoretical convergence rates and the influence of residual accuracy on conservation properties.
arXiv:2607.15087v1 Announce Type: new
Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful framework for solving forward and inverse partial differential equations (PDEs), but conventional real-valued PINNs (RV-PINNs) often suffer from spectral bias, limited expressivity, and reduced accuracy for high-frequency, oscillatory, and phase-dependent dynamics. In this work, we propose a generalized split complex-valued physics-informed neural network (SCV-PINN), in which network parameters and latent representations are defined in the complex domain. The framework employs split complex-valued activation functions by independently applying standard real-valued activations to the real and imaginary components, providing numerical stability, computational efficiency, and improved approximation capability. This formulation enables simultaneous learning of amplitude and phase information, enhancing the representation of nonlinear and oscillatory systems. Extensive ablation studies evaluate different split activation functions and collocation sampling strategies. The proposed framework is validated on forward and inverse PDE benchmarks including Burgers, Allen-Cahn, Korteweg-de Vries, nonlinear Schrodinger, Helmholtz, Poisson, Kovasznay flow (Re = 20), lid-driven cavity flow (Re = 100), the Lorenz system, inverse Burgers, inverse Navier-Stokes (Re = 100), and a three-dimensional Navier-Stokes Beltrami flow. For the Beltrami benchmark, SCV-PINN achieves a relative L2 error of 4.07 x 10^-5. Numerical results consistently demonstrate lower relative L2 errors and more accurate parameter identification than RV-PINNs and several existing PINN variants. The proposed SCV-PINN provides a robust and generalized extension of standard PINNs for complex-valued, multiscale, oscillatory, high-dimensional, and real-valued nonlinear PDEs.
arXiv:2607.15088v1 Announce Type: new
Abstract: Large Faraday rotations can be generated by circular birefringence of atomic samples in an axial magnetic field in the vicinity of atomic resonance lines. The Faraday angle is a function of the magnetic field strength, the optical density of the atomic sample which may be varied by changing the temperature of the atomic gas, and of course the optical detuning from the transition frequencies. More generally, magneto-optical effects in atomic samples include circular dichroism in addition to birefringence, resulting in a modification of the ellipticity as well as the polarisation alignment. Usually such effects are investigated for homogeneous linear polarisations, but the mechanisms apply also to polarisation structures such as vector vortices. We investigate the effect of optical activity of a rubidium vapour in the Hyperfine Paschen-Back regime, for the example of an azimuthally polarised input light beam. We show that for low atomic densities, circular birefringence dominates over dichroism, and azimuthal polarisation is rotated towards radial polarisation. The rotation angle increases with increasing optical densities. At high vapour temperatures, dichroism becomes more and more relevant, leading to intricate variations of both alignment and ellipticity.
arXiv:2607.15094v1 Announce Type: new
Abstract: Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every retrieval direction to the same stability-plasticity trade-off. We propose AlphaWiSE, a post-hoc weight-space interpolation method that composes two frozen source checkpoints. For each aligned parameter tensor identified by its checkpoint key, AlphaWiSE fits one scalar interpolation coefficient shared by all tensor entries. The coefficients are fitted on a smaller exemplar memory and used to materialize one interpolated checkpoint. The deployed model has the same architecture and parameter count as either source checkpoint, which does not require additional inference time. Extensive experiments on audio-image-text retrieval show consistent improvements over strong continual-learning baselines across multiple retrieval directions and evaluation metrics.