arXiv:2607.15362v1 Announce Type: new
Abstract: Resolving multiscale fluid flows or boundary layers effectively requires the use of nonuniform meshes with local grid clustering. The standard lattice Boltzmann method (LBM), a kinetic theory-based approach for computational fluid dynamics, however, is restricted to the use of uniform Cartesian grids. We present new and improved formulations of the LBM that accommodate continuously varying spatial grids via coordinate transformations to simulate the Navier-Stokes equations (NSE) in the general orthogonal coordinates (GOC). They are constructed using a Chapman-Enskog analysis to specify the equilibrium moments of the distribution functions and the geometric force terms used in the collision step to be dependent on the local metric factors and their spatial derivatives, along with the density, momentum and their fluxes, and some correction terms related to the normal velocity gradients so as to accurately represent the NSE in the GOC. The resulting GOC-LBM importantly maintains the simplicity of the collide-and-stream approach and is Galilean invariant that is free of the cubic velocity artifacts. Our GOC-LBM is general and modular in that it can be used with any collision model with appropriate modifications to the equilibria and forcing terms. We present its implementation details for a variety of collision models while the central moments-based model using multiple relaxation times was found to be the most robust in practical implementations. We validate the GOC-LBM through numerical simulations for various benchmark flow problems. Moreover, we demonstrate significant computational advantages of our approach for a case study on simulating boundary layer flows efficiently that involves coupling the GOC-LBM for the NSE with a new GOC-LB scheme for solving the magnetic induction equation for magnetohydrodynamics (MHD), and for another case study involving orthogonal curvilinear grids.
Science Journals
arXiv:2607.15828v1 Announce Type: new
Abstract: Autonomous exploration of unknown 3D environments is traditionally driven by coverage-maximizing geometric heuristics. However, these methods typically determine exploration targets without considering the underlying structural context. This leads to inefficient trajectories often limiting the fidelity of the final 3D reconstruction. To bridge the gap between spatial coverage and reconstruction quality, we introduce a novel paradigm: reframing exploration as a geometric anomaly minimization problem. We present SCAGE: SCene Anomaly Guided Exploration, a novel autonomous exploration framework that operates directly on unstructured 3D point clouds. Instead of blindly chasing volumetric boundaries, we equip the robot with a foundational understanding of standard indoor architecture. As the robot navigates, it continuously evaluates its live 3D observations against these learned expectations. When the incoming geometry contradicts the learned priors of a typical indoor environment, such as a fragmented wall or a partial table, the system flags these regions as scene anomalies. These geometric inconsistencies act as a guiding signal, naturally drawing the robot to investigate and resolve these structural anomalies from optimal vantage points. By actively targeting poorly reconstructed regions rather than just empty space, our approach seamlessly couples spatial discovery with high-fidelity mapping. Extensive evaluations demonstrate that SCAGE achieves superior volumetric coverage (~90% in all scenes) and higher 3D reconstruction quality compared to state-of-the-art baselines.
arXiv:2607.15413v1 Announce Type: new
Abstract: Existing fast GPU error-bounded lossy compressors have achieved high throughput through pure-GPU single-kernel designs, but their compression ratios remain limited because they typically apply a fixed first-order predictor on independent blocks. We propose FSZ, a GPU error-bounded lossy compressor that redesigns the prediction stage with three mutually reinforcing algorithmic innovations to achieve both higher compression ratios and higher throughput within a single CUDA kernel: (1) cross-block prediction state carries Lorenzo prediction state across block boundaries within 256-element tiles, eliminating 7 out of 8 boundary residuals that inflate encoding rates; (2) per-tile adaptive multi-order prediction and centering adaptively selects the best compression strategy per tile from first-order, second-order, and centering variants; and (3) a single-pass four-way evaluation exploits a mathematical property of finite differences to evaluate all variants from a single data read, enabling richer prediction within the same bandwidth budget as a fixed predictor. Experiments on NVIDIA GH200 GPU with 8 real-world application datasets show that FSZ outperforms cuSZp-P by up to 10.95x and the state-of-the-art cuSZp-O by up to 2.92x in compression ratio. Notably, these gains come with no throughput penalty: FSZ simultaneously achieves the highest average throughput (676 GB/s compression, 785 GB/s decompression) among all evaluated compressors.
arXiv:2607.15892v1 Announce Type: new
Abstract: Studies of spin-dependent effects at the Nuclotron/NICA accelerator complex at JINR require precise measurements of the deuteron and proton beam polarization. The vector polarization of the deuteron beam was measured at the energies of 200, 500, 550, and 650 MeV/nucleon by a detection system of scintillation counters placed at the Nuclotron internal target. Considering the deuteron beam as a beam of weakly bound protons and neutrons, the asymmetries of scattering of protons from deuterons on polyethylene and carbon targets were determined. The polarization of the polarized proton beam accelerated for the first time at the Nuclotron up to 500 MeV was also measured.
arXiv:2607.16153v1 Announce Type: new
Abstract: Computation of zigzag persistence has progressed in recent years, with results showing that complexities of many problems closely align with those in the non-zigzag setting. The major efficiency gap now lies in the updating of zigzag representatives. In this paper, we propose efficient algorithms for updating zigzag representatives based on a recent algorithm for extracting zigzag representatives from a $R=DV$ decomposition of a constructed non-zigzag. The main difficulty for designing our update algorithms lies in the adjacency change occurring in two operations that elongate or shorten a filtration. Despite the adjacency change, we find that the update can still be done efficiently in quadratic time.
arXiv:2607.15527v1 Announce Type: new
Abstract: Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and the development of anomaly detection models. However, the severe shortage of flood data in real-world environments, combined with the inherent distortions of fisheye lens images, which are used for urban surveillance, has made high-precision simulations challenging. To address this, we propose a new physical simulation system PhysFlood that leverages Diffusion Models to synthesize realistic floods from just a single image captured by a fisheye lens. Our system not only enables simulation from a single image, but also features the ability to freely control and generate diverse flood scenarios by manipulating physically meaningful variables, such as water levels. In our evaluation experiments, we conducted a qualitative human study and demonstrated that the simulation images generated by PhysFlood exhibit both acceptable realism and robustness.
arXiv:2607.15605v1 Announce Type: new
Abstract: Focal cortical dysplasia (FCD) is one of the leading structural causes of drug-resistant focal epilepsy, yet its subtle and heterogeneous imaging characteristics make accurate identification and delineation challenging on conventional magnetic resonance imaging (MRI). Although T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) images are routinely acquired for presurgical evaluation, the contribution of different MRI representations to deep learning-based FCD segmentation remains poorly understood. In this study, we present a systematic benchmark of MRI representations for automated FCD segmentation using the nnU-Net framework. A publicly available presurgical MRI dataset comprising 85 FCD subjects and 25 healthy controls was used to evaluate eight input configurations, including conventional MRI contrasts (T1w and FLAIR), ratio-derived representations, and their multimodal combinations. To isolate the effect of MRI representation, all experiments employed identical preprocessing, network architecture, optimization strategy, and five-fold cross-validation. Among the evaluated single-modality representations, FLAIR achieved the strongest overall performance, whereas ratio-derived representations alone were insufficient for reliable identification of subtle FCD. Incorporating ratio-derived representations with conventional T1w and FLAIR images consistently improved lesion delineation, with the four-channel multimodal configuration achieving the highest overall Dice score (0.376), representing a 5.0% relative improvement over the conventional T1w+FLAIR representation. These findings demonstrate that MRI representation design is an important yet underexplored component of deep learning-based FCD segmentation and should be optimized alongside network architecture.
arXiv:2507.22854v3 Announce Type: replace
Abstract: We propose novel classical and quantum online algorithms for learning finite- and infinite-horizon Markov Decision Processes (MDPs). Our algorithms are based on a hybrid online-offline reinforcement learning model wherein the agent can, from time to time, freely interact with the environment in a generative sampling fashion, i.e., by having access to a "simulator". By employing known classical and new quantum algorithms for approximating optimal policies under a generative model within our learning algorithms, we show that it is possible to avoid several paradigms from RL like "optimism in the face of uncertainty" and "posterior sampling" and instead compute and use optimal policies directly, which yields better regret bounds compared to previous works. Our quantum algorithms obtain regret bounds which only a $\operatorname{poly}\log{T}$ dependence on the number of time steps $T$, thus breaking the $O(\sqrt{T})$ classical barrier. Our infinite-horizon discounted regret bound is brand new, while in the finite- and infinite-horizon undiscounted settings, our results match the time dependence of some prior quantum works, but with improved dependence on other parameters like state space size $S$ and action space size $A$.
arXiv:2607.15925v1 Announce Type: new
Abstract: Microsecond conformational changes underlie many protein functions, but ensemble averaging has been needed to observe them without labels. Single-shot measurements on individual proteins have had insufficient speed, while protein Brownian-motion has obscured signals. Here, we report a fibre-integrated silicon-photonic sensor that overcomes these barriers, resolving protein dynamics at sub-microsecond speeds in continuous single-shot measurements that can extend over minutes. This is achieved by combining far-sub-wavelength optical field confinement with high optical field uniformity that suppresses protein Brownian-motion by a factor of sixty. In single-shot measurements on ferritin molecules, we observe tens of thousands of transitions consistent with conformational fluctuations of the ferritin shell, resolving them over timescales as short as 400 ns. The ability to continuously monitor transitions over long times reveals switching kinetics, memory effects and molecular heterogeneity hidden in ensemble averages. This opens a new path to improved mechanistic understanding of protein function.
arXiv:2607.15560v1 Announce Type: new
Abstract: Physics-informed neural networks (PINNs) are unusually sensitive to interacting choices of architecture, activation, loss weighting, collocation, optimization, and constraint enforcement. Large language models (LLMs) can propose these choices, but independent recommendations do not accumulate experience from previously trained PINNs. We propose a closed-loop evolutionary algorithm that guides an LLM to generate complete, executable PINN configurations across generations, using measured training outcomes to determine subsequent search decisions. The algorithm maintains an evaluated population and lineage, applies parent-conditioned mutation and crossover, preserves elite and diverse solutions, rejects effective duplicates, and converts parent-relative successes and failures into the next-generation context supplied to the LLM. Every proposed configuration is executed directly under an exact optimizer-step budget. On a one-dimensional multiscale wave equation, two independent ten-generation runs trained 60 PINNs for 600,000 optimizer steps. In both runs, the best configuration appeared in the final generation, with best mean-squared error reduced by 2.97\% and 95.38\% relative to the initial population. The stronger run validated residual connections and increased depth on separate branches, combined them in a later generation, and then refined width and collocation density. It also revealed that low solution error can coexist with a high PDE residual. These results demonstrate the feasibility of evolutionary-algorithm-guided LLMs for PINN design on a controlled PDE while motivating broader, physics-aware evaluation.
arXiv:2607.15843v1 Announce Type: new
Abstract: Frequency-domain dual-comb ranging combines rapid acquisition with interferometric sensitivity, but high-performance implementations often rely on mutually coherent or actively stabilised comb sources. Free-running sources can reduce this hardware burden, but their phase noise and drift of the optical frequency offset can blur radio-frequency (RF) comb teeth and weaken probe-reference phase correlation. Previous phase-slope implementations have therefore relied on sufficiently resolved RF teeth, within-coherence-length probe-reference paths or explicit digital tracking of these fluctuations. Here we demonstrate a low-cost frequency-domain dual-comb ranging architecture that combines independent free-running distributed-feedback (DFB) lasers with conjugate phase-noise cancellation (CPNC). By forming a self-conjugate signal before the phases of individual RF-comb teeth are extracted, CPNC cancels the common laser phase factor and drifting optical-frequency-offset term while retaining the distance-dependent phase slope. Using electro-optic combs seeded by DFB lasers with linewidths of 12 MHz and 9 MHz, we achieve an Allan deviation of $219~\mathrm{nm}$ at $246~\mu\mathrm{s}$ and reduce the single-frame distance standard deviation from $558~\mu\mathrm{m}$ to $9.31~\mu\mathrm{m}$ with CPNC. Across the tested megahertz-linewidth configurations, CPNC delivered minimum Allan deviations below $250~\mathrm{nm}$. These results show that CPNC enables submicrometre ranging in a low-cost frequency-domain dual-comb architecture with reduced source-stabilisation and phase-management complexity.
arXiv:2607.15321v1 Announce Type: new
Abstract: AI-generated videos (AIGVs) typically contain subtle temporal artifacts that arise from inter-frame inconsistencies rather than within individual frames. A detector that captures such artifacts should therefore benefit from video pretrained backbones over image only ones. In practice, however, video backbones with standard global readouts often fail to outperform strong image pretrained probes on AIGV benchmarks. We attribute this gap to excessive spatiotemporal aggregation in the readout. Video pretrained backbones tend to compress each frame into a single global descriptor. This compression suppresses local patch level temporal dynamics and discards inter patch relations, which are precisely the cues that AIGV detection most reliably depends on. Based on this, we propose Velocity Gated Patch Velocity Profiling (V-PVP), a lightweight readout that replaces only the aggregation layer with two parallel streams over the patch velocity field, adding only about $0.5$M trainable parameters. V-PVP serves as a general plug-and-play module that consistently improves performance across diverse video backbones under both end-to-end fine-tuning and linear probing settings. Our method reaches \textbf{95.28} AUC on AIGVDBench while keeping the backbone fully frozen. The results show that simply replacing the aggregation layer reactivates the temporal potential of frozen video backbones, restoring their advantage on AIGV detection. Code is available at https://anonymous.4open.science/r/PVP-81B3/.
arXiv:2607.15593v1 Announce Type: new
Abstract: LLM agents increasingly rely on tool calling to act on external systems, and the Model Context Protocol (MCP) has quickly become its de facto interface. Operating MCP at cloud scale, however, becomes difficult. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development also creates ongoing compatibility cost. On the agent side, the number of accessible tool is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity.
We present a cloud-scale gateway system for MCP service. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing to the gateway. Hybrid retrieval sustains 98% Top-15 recall; it scales agent tool access to 3,000+ with high tool selection accuracy, and reduces tool selection time by $8.9\times$ and token usage by $23.8\times$, with low per-call overhead, stable under scale-out. Finally, we share the lessons learned from deploying the gateway system in production.
arXiv:2607.15929v1 Announce Type: new
Abstract: The approach of squeezing more transistors in the same area in order to speed up computing is no longer effective. Currently, researchers and engineers are searching for novel solutions that offer faster computing. One of these solutions is to compute where you store, known as in-memory computing. Resistive random access memories (ReRAMs), which are based on memristor crossbar arrays, enable in-memory computing. Moreover, ReRAMs offer large storage capacity associated with energy efficiency. In this work, we focus on storing digital data in memristor crossbar arrays. A critical challenge here is the sneak-path problem, occurring when there is a rectangle on the array with three low and one high resistances at the corners. The electric current in this case is prone to sneaking through the low-resistance path upon reading, which results in the high resistance data becoming erroneous. In this paper, we propose effective constrained coding solutions to the sneak-path problem after finding the expected number of sneak paths over a two-dimensional array given their circumferences. In particular, we adopt a literature model where $b$ rows on the crossbar array are read simultaneously while the others are grounded, and we design capacity-achieving non-binary constrained codes for the cases of $b=2$ and $b=3$. We focus more on the sneak paths with shorter circumferences as they are more detrimental. Here, GF refers to Galois field. Our GF$(4)$ codes, for $b=2$, and GF$(8)$ codes, for $b=3$, are a class of lexicographically-ordered constrained (LOCO) codes, and we call them resistive-LOCO (RES-LOCO) codes. RES-LOCO codes operate horizontally, and we also suggest a run-length-limited scheme for coding data on the crossbar array vertically to mitigate the sneak-path problem for $b=4$. We experimentally demonstrate the effectiveness of our RES-LOCO codes for various array setups.
arXiv:2607.15591v1 Announce Type: new
Abstract: Large language models (LLMs) are transforming recommender systems from matching co-occurrence patterns in historical behavior toward reasoning about the intent that drives it. RecGPT-V1 pioneered this paradigm on Taobao by centering user understanding, and RecGPT-V2 scaled it via coordinated multi-agent reasoning; both are deployed in production with consistent gains in user experience and commercial outcomes. However, operating RecGPT at scale reveals three challenges: (1) stateless behavior modeling, where each request reprocesses full user history, wasting computation and discarding prior analysis; (2) a tag-to-item information bottleneck, where natural-language tags form a lossy channel between user understanding and item grounding; and (3) inefficient explicit reasoning, whose lengthy chain-of-thought incurs untenable latency and compute overhead.
We present RecGPT-V3, a stateful, hybrid-modal recommender that reasons over natural language for open-world knowledge and Semantic IDs (SIDs) for concrete item grounding. A Memory Hub maintains structured, continually evolving user memory that distills long-horizon behavior into condensed units, cutting user-modeling computation by 55.8%. A Hybrid-modal Foundation Model allows the LLM jointly reason over text tags and SIDs, opening a high-bandwidth channel into the item space. Latent Intent Reasoning internalizes verbose rationales into compact learnable latent tokens that remain decodable into readable explanations, lowering output token cost by 200x. Deployed in Taobao's "Guess What You Like" feed, RecGPT-V3 achieves consistent gains in large-scale online A/B tests: IPV +1.28%, CTR +1.00%, TC +1.97%, GMV +3.97%, while cutting end-to-end serving resource consumption by 52.4%.
arXiv:2508.00042v2 Announce Type: replace
Abstract: Machine learning models deployed in non-stationary environments degrade silently, since as the input distribution drifts their accuracy decays without an error signal and without labels to reveal it. Sustaining reliable AI therefore requires a concept-drift detector that acts as an external observer of the deployed model, monitoring it using unlabeled operational data alone, so that an MLOps actuator triggers retraining and redeployment only when it is warranted. This paper contributes two concept drift detectors, namely Confidence-Filtered Pseudo-Label Transfer (CFPT) and TabAutoDrift, which combine representation learning with statistical testing to compute an expected utility score that signals whether a deployed model should be retrained, without requiring ground-truth labels after deployment. The detectors are evaluated on two emerging, label-scarce wireless application domains in which post deployment ground truth is effectively unavailable, namely outdoor fingerprinting-based localization and link-anomaly detection. They outperform the classical detectors ADWIN, DDM, and CUSUM, attaining a drift-detection F1-score between 0.88 and 0.94 in the fingerprinting use case and between 0.80 and 1.00 in the link-anomaly use case, up to 0.24 higher than the strongest classical detector. Interpreted as reliability decisions, this precision indicates that the proposed detectors signal retraining more dependably.
arXiv:2508.00521v3 Announce Type: replace
Abstract: Accurate measurement of surface plasmon polariton (SPP) dispersion remains challenging, as conventional angle-resolved techniques are limited by surface quality, diffraction artifacts, and geometry-induced band folding. Here, we show that SPP dispersion can be reconstructed from transmission spectra of plasmonic gratings with subwavelength apertures acting as Fabry-P\'erot (FP) cavities. The approach harnesses modal hybridization between localized FP modes and SPPs, resolved using non-Hermitian eigenmode decomposition and validated by finite-difference time-domain simulations. {\omega}-k dispersion mapping is achieved by varying the grating periodicity, with each structure probing a distinct in-plane momentum state. Geometry- and material-dependent corrections for aperture-induced leakage and dispersive phase shifts yield reconstructed relations in close agreement with eigenmode calculations across non-dispersive, Drude, and Drude-Lorentz models as well as experimental optical datasets spanning metals, oxides, and nitrides. The method is material-agnostic and requires no momentum-resolved instrumentation. Sensitivity to fabrication-induced wall roughness is also assessed: FP resonance positions remain spectrally stable with no measurable linewidth broadening across the explored perturbation range, and the modal field topology is largely preserved throughout. However, transmitted amplitude decreases monotonically owing to enhanced ohmic absorption at the perturbed boundaries.
arXiv:2508.05321v4 Announce Type: replace
Abstract: Assume you encounter an inverse problem that shall be solved for a large number of data, but no ground-truth data is available. To emulate this, in this study we assume it is unknown how to solve the imaging problem of Computed Tomography. We introduce an unsupervised deep learning framework that leverages the inherent similarities between iterative reconstruction, Deep Image Prior (DIP), and unrolled optimization schemes. Our specific contribution is a training framework for amortized reconstruction: After training on a dataset without any image-domain ground truth, reconstruction of an unseen scan reduces to a single network forward pass. We demonstrate the feasibility of reconstructing images from measurement data by pure network inference, without additional gradient steps for unseen samples. Our method is evaluated on the two-dimensional 2DeteCT dataset. Within a controlled, geometry-matched benchmark, our reconstructions are competitive with, or better than, filtered back-projection, maximum-likelihood reconstruction, and a supervised network of identical architecture. Compared to a per-image DIP baseline, our method reaches similar quality while replacing the costly per-instance optimization with a single forward pass, yielding a speed-up of about four orders of magnitude. This makes it a promising candidate for time-critical imaging applications. Future work will address multi-dataset adaptability, counter-measures against over-smoothing, advanced uncertainty quantification, and further medical-imaging inverse problems.
arXiv:2607.15634v1 Announce Type: new
Abstract: Audio mixing style encompasses the artistic and technical decisions a mix engineer makes, including level balancing, spatialization, and the choice, ordering, and parameterization of audio effects (FX) on each stem. FX chains are a key determinant of this style, yet existing approaches to modeling them remain limited. Some operate on stereo mixtures without explicit per-stem FX chain modeling, others fix the number or type of effects per track, and many require differentiable effect implementations or scarce multitrack datasets. We present StemFX, a framework that learns mixing style representations by autoregressively predicting variable-length FX chains on source-separated stems. A Transformer decoder predicts tokenized FX chains autoregressively, while a band-split multi-band CNN encoder with FiLM conditioning captures per-stem spectral structure. To enable large-scale paired training, we extract pseudo-stems from about 105K songs via source separation and augment them using MultiAFx, a toolkit unifying 85 audio effects from 7 Python libraries. Evaluated on mixing style retrieval, StemFX outperforms all baseline models across all tested chain lengths. On paired mixing style transfer, StemFX achieves the best spectral fidelity and the highest listener preference, over 4000 times faster than iterative optimization.
arXiv:2607.15643v1 Announce Type: new
Abstract: We investigate how the scaling of the interior-penalty parameter affects nonsymmetric interior-penalty Galerkin (NIPG) discretizations of the viscous rotating shallow-water equations in geopotential variables. The hyperbolic terms are approximated by a local Lax--Friedrichs flux, while viscosity acts on the momentum variables through a penalty law $\mu_e=\sigma h_e^{-\beta}$. The standard choice $\beta=1$ and the super-penalized choice $\beta=3$ are compared with a symmetric interior-penalty Galerkin reference. For the diffusion form, we establish consistency, continuity for $\beta\ge 1$, and an exact coercivity identity in the momentum DG seminorm. Manufactured-solution tests show that super-penalization can recover the expected momentum $L^2$ accuracy, whereas the coupled geopotential variable need not exhibit the same improvement. Rotating and topography-aware tests further show that the standard scaling generally gives the better accuracy-cost compromise for the explicit implementation considered here.
arXiv:2607.15647v1 Announce Type: new
Abstract: LEED v4.1 BD+C certification remains a document-intensive process that requires reviewers to read hundreds of pages of project evidence and apply credit-specific threshold logic by hand. This paper investigates whether small, locally deployed language models can perform meaningful screening of LEED documentation and how deterministic symbolic components should share that work. A neuro-symbolic pipeline is introduced that aligns project PDFs to LEED credit sections, retrieves evidence with credit-aware keyword signatures, verifies compliance with a locally hosted 4-billion-parameter language model, and applies a LEED-specific numeric checker to quantitative thresholds. Experiments on four university buildings (484 PDFs, 153 credit-level decisions) show that a 4-billion-parameter model (gemma3:4b) is the strongest text-only core verifier, achieving 67.3% accuracy and outperforming a larger 8-billion-parameter model (llama3.1:8b) in this task. The deterministic numeric checker corrects arithmetic errors on key quantitative credits, moving EA-p2 from 50% to 100% accuracy and improving several other credits when required values are reliably extracted. At the same time, the full neuro-symbolic configuration achieves 61.6% overall accuracy, trailing the best text-only baseline due to extraction failures and conservative behavior on qualitative categories. Systematic ablations show that adding low-resolution drawing images (150-300 dpi) consistently reduces accuracy, and that prompt effectiveness depends on the building's ground-truth PASS rate: rubric prompts perform best on documentation-rich projects, while chain-of-thought prompts perform best on documentation-lean projects. Within the specific scope of LEED v4.1 BD+C compliance verification over raw project documentation, this pipeline and its baselines provide an initial reproducible reference point for both accuracy and failure modes.
arXiv:2607.15656v1 Announce Type: new
Abstract: Developing autonomous hydraulic excavators is constrained by limited access to physical machines and the high cost of real-world experimentation. This paper proposes a simulation-to-real framework for learning a system-level digital surrogate using Long Short-Term Memory (LSTM) networks. Instead of modeling internal dynamics, the excavator is treated as an input-output operator, and the surrogate is trained to reproduce its closed-loop behavior under identical control inputs. The approach is first validated in a MuJoCo simulation environment and then transferred to a real excavator. To address measurement inconsistencies in real-world data, a consistency-aware state estimation method based on adaptive Kalman filtering is introduced. Experimental results demonstrate that the learned surrogate achieves high fidelity in both angular velocity and long-horizon trajectory reproduction under closed-loop autoregressive evaluation. These results confirm that the proposed model can serve as a drop-in surrogate for both simulation and physical systems, enabling scalable and efficient development of excavation automation algorithms.
arXiv:2607.15705v1 Announce Type: new
Abstract: Accurate load forecasting at multiple grid levels is essential for future smart grids, ranging from aggregated control area forecasts for balancing supply and demand to forecasts of individual end-consumer loads for demand-side management and energy management systems. We present a comprehensive benchmark for load forecasting across grid levels, comprising three datasets that represent a transmission system operator control area, low-voltage grid feeders, and individual end consumers. We evaluate ten methods for short-term load forecasting and find that Transformer-based approaches consistently outperform established methods, reducing forecast error by 6.6-10.7 %. To analyze the impact of architectural design, we introduce YAformer, a flexible Transformer architecture that integrates modifications from prior work and is optimized via hyperparameter optimization. However, the standard Transformer achieves superior performance, suggesting that these architectural modifications are not required for accurate load forecasting. We further evaluate the Transformer-based time-series foundation model Chronos-2, which demonstrates competitive zero-shot performance on two datasets but fails to accurately capture special events in the TSO data. Detailed analyses reveal model-specific strengths and weaknesses, and ablation studies highlight the importance of long input contexts, covariates and continuous retraining - aspects that are often overlooked in the time-series forecasting literature.
arXiv:2508.09860v2 Announce Type: replace
Abstract: Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals in collaborative content creation. This direction is especially relevant in procedural content generation via reinforcement learning (PCGRL), which is intended to serve as a tool for human designers. However, existing systems often fall short of exhibiting human-centered behavior, limiting the practical utility of AI-driven generation tools in real-world design workflows. In this paper, we propose VIPCGRL (Vision-Instruction PCGRL), a novel deep reinforcement learning framework that incorporates three modalities-text, level, and sketches-to extend control modality and enhance human-likeness. We introduce a shared embedding space trained via quadruple contrastive learning across modalities and human-AI styles, and align the policy using an auxiliary reward based on embedding similarity. Experimental results show that VIPCGRL outperforms existing baselines in human-likeness, as validated by both quantitative metrics and human evaluations. The code and dataset are available at https://github.com/bic4907/VIPCGRL.
arXiv:2607.15677v1 Announce Type: new
Abstract: Green roofs are increasingly promoted as nature-based measures for reducing building energy demand, yet their performance in New Zealand's oceanic climates and under future weather remains insufficiently quantified. This condensed study compares an extensive green roof with a conventional bare roof on a standardized single-storey dwelling in Auckland, Christchurch, and Wellington. Dynamic annual simulations were conducted in DesignBuilder/EnergyPlus using present-day EnergyPlus Weather files and 2050 weather files generated with CCWorldWeatherGen. All non-roof building parameters were held constant so that differences in total fuel consumption (TFC) for heating and cooling could be attributed to the roof system. Under present weather, annual TFC decreased by approximately 3.1% in Auckland, 2.3% in Christchurch, and 1.5% in Wellington. Under 2050 weather, the corresponding reductions were 3.3%, 2.6%, and 1.1%. Summer benefits were larger in Auckland and Christchurch, reaching about 9.0% and 5.6%, respectively, in 2050, but remained marginal in Wellington. The findings show that green roofs can provide modest annual energy savings in oceanic climates, with stronger value as a summer heat-mitigation measure in warmer locations. Performance is strongly climate-dependent and should not be generalized without local simulation or field validation.