arXiv:2509.03664v2 Announce Type: replace Abstract: We reproduce the consistently-seen experimental voltage versus pressure (V-p) dependence of DC magnetron sputtering (DCMS) with 2D-RZ particle-in-cell (PIC) simulation. Informed by PIC simulation, we develop a steady-state, 1D-axial fluid model of the sheath and presheath that also reproduces this V-p dependence. The V-p dependence is the relationship between the steady-state voltage needed to maintain a constant discharge current and the neutral gas pressure. V-p dependence is fundamental to device performance, but has not previously been reproduced with simulation or satisfactorily explained. We find that the decrease in voltage with increasing pressure is not due to electron recapture at the cathode. Rather, the constant current dictates a constant global ionization rate, so the voltage decrease compensates for the increase in neutral gas density by lowering the energy of the plasma electrons, which decreases their ionization probability. The PIC simulations also reveal that the presheath and bulk plasma are unaffected by the electron reflection coefficient at the cathode; the only effect of increasing reflection is a reduction in the sheath voltage and width. In addition to the potential structure, we explore how pressure affects the plasma density, particle drifts, and particle energy distributions.
Science Journals
arXiv:2606.29093v1 Announce Type: new Abstract: A deep defogging pipeline pretrained on controlled laboratory fog and fine-tuned with domain-randomized synthetic fog applied to clear outdoor scenes generalizes across a graded sequence of out-of-distribution settings with no target-domain training, from chamber-free free-flowing fog to iPhone video recorded through an aircraft cabin window in flight, an entirely unseen sensor, scene, and optical path. This directly addresses an open transfer limitation reported for real-world binocular defogging. Two design choices support the transfer. First, a single-camera fog imager photographs a flat-panel display through an artificial-fog enclosure with a fixed 114~mm scattering path, producing 5{,}495 pixel-aligned foggy/clear pairs. Exact registration permits a paired Laplacian ratio that predicts per-image restoration quality far better than single-image proxies (Spearman $\rho = 0.632$ versus $0.399$) and supports pixel-exact $L_1$ reconstruction training that avoids adversarial hallucination. Second, the fog-chamber checkpoint is fine-tuned on Mapillary Vistas crops overlaid with on-the-fly randomized synthetic fog spanning a broad range of strengths, spatial variations, airlights, and noise conditions. On a 552-image held-out split, a uniform comparison of 30 restoration backbones places NAFNet at the top (24.33~dB~/~0.7912~SSIM), with a compact alternative within 1.29~dB at 3\% of the parameter count, and a ResNet-50 classifier confirms that the restoration preserves semantic content rather than only pixel-level structure. On unpaired aircraft-window video, NIQE decreases from a mean of 6.22 to 4.97 after fine-tuning, with temporally stable output across full-motion sequences. The same backbone, under paired supervision, also reaches 20.71~dB~/~0.683~SSIM on a non-overlapping O-HAZE/NH-HAZE split (a transferability check rather than a competitive ranking).
arXiv:2507.07445v3 Announce Type: replace Abstract: Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously. To bridge this gap, we introduce StarDojo, a novel benchmark based on Stardew Valley, designed to assess AI agents in open-ended production-living simulations. In StarDojo, agents are tasked to perform essential livelihood activities such as farming and crafting, while simultaneously engaging in social interactions to establish relationships within a vibrant community. StarDojo features 1,000 meticulously curated tasks across five key domains: farming, crafting, exploration, combat, and social interactions. Additionally, we provide a compact subset of 100 representative tasks for efficient model evaluation. The benchmark offers a unified, user-friendly interface that eliminates the need for keyboard and mouse control, supports all major operating systems, and enables the parallel execution of multiple environment instances, making it particularly well-suited for evaluating the most capable foundation agents, powered by multimodal large language models (MLLMs). Extensive evaluations of state-of-the-art MLLMs agents demonstrate substantial limitations, with the best-performing model, GPT-4.1, achieving only a 12.7% success rate, primarily due to challenges in visual understanding, multimodal reasoning and low-level manipulation. As a user-friendly environment and benchmark, StarDojo aims to facilitate further research towards robust, open-ended agents in complex production-living environments.
arXiv:2509.07201v2 Announce Type: replace Abstract: This paper proposes a linear input-output observer design methodology for a population of systems in which each observer uses knowledge of the linear time-invariant dynamics of the particular device. Observers are typically composed of a known model of the system and a correction mechanism to produce an estimate of the state. The proposed design procedure characterizes the variation within the population in the frequency domain and synthesizes a single robust correction filter. The correction filter is compatible with all system models that satisfy the variation characterization such that a given level of estimation performance is guaranteed. This is accomplished by posing a robust performance problem using the observer error dynamics and solving it using $DK$-iteration. The design procedure is experimentally demonstrated on a flexible joint robotic manipulator with varied joint stiffnesses. It is shown that the proposed method that uses a single correction filter achieves comparable estimation performance to a method that uses a correction gain tailored toward each joint stiffness configuration.
arXiv:2507.15431v4 Announce Type: replace Abstract: We offer a theoretical mathematical background through Lagrangian optimization on the unit hyperspherical manifold and its tangential structure. Our methods can be categorized as inexact since our methods are projection-based and since we will perturb the functional optimization with epsilon-type quantities. We draw connections to the attention mechanism and the Transformer since it exists as a flow map in the tangent fiber for each token along the high-dimensional unit sphere. Our motivation for this work is primarily twofold: we study the attention mechanism under its flow map and its relations to traditional calculus of variations and Lagrangian optimization; and we study a range of calculus of variations on the unit hypersphere that appeal to a broader mathematical lens in approximating, variational contexts.
arXiv:2507.21136v2 Announce Type: replace Abstract: Conventional dimensionality reduction methods mainly optimize variance or correlation, leaving statistical dependence, data diversity, contrast, and interpretability under addressed. We propose three new independence criteria for designing supervised and unsupervised dimensionality reduction (DR) methods, aiming to improve feature extraction and representation quality. Our framework combines linear and nonlinear formulations and is evaluated using contrast, classification accuracy, and interpretability measures. The interpretability of eigenfaces helps to effectively summarize dominant class-specific structures and trends within representative images. Evaluated on MNIST and a Gender face dataset for classification and reconstruction, our methods achieve significant improvements in contrast (up to $+$20.1\%), accuracy (up to $+$17.4\%), and interpretability (up to $+$120.0\%) over Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), Linear Discriminant Analysis (LDA), and Variational Autoencoder (VAE) baselines, while also improving VAE reconstruction performance by 9.5\%. These results suggest a promising direction for interpretable representation learning based on statistical dependence and independence criteria.
arXiv:2509.12159v2 Announce Type: replace Abstract: Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional code generation due to the large number of input image tokens and extensive output code tokens required. Our comprehensive study identifies significant redundancies in both image and code tokens that exacerbate computational complexity and hinder focus on key UI elements, resulting in excessively lengthy and often invalid HTML files. We propose EfficientUICoder, a compression framework for efficient UI code generation with three key components. First, Element and Layout-aware Token Compression preserves essential UI information by detecting element regions and constructing UI element trees. Second, Region-aware Token Refinement leverages attention scores to discard low-attention tokens from selected regions while integrating high-attention tokens from unselected regions. Third, Adaptive Duplicate Token Suppression dynamically reduces repetitive generation by tracking HTML/CSS structure frequencies and applying exponential penalties. Extensive experiments show EfficientUICoder achieves a 55%-60% compression ratio without compromising webpage quality and delivers superior efficiency improvements: reducing computational cost by 44.9%, generated tokens by 41.4%, prefill time by 46.6%, and inference time by 48.8% on 34B-level MLLMs. Code is available at https://github.com/WebPAI/EfficientUICoder.
arXiv:2509.13561v2 Announce Type: replace Abstract: Progressive Web App (PWA) installation is critical for integrating web and mobile app functionalities, offering a seamless user experience. However, ensuring the security of the PWA installation lifecycle is essential for maintaining user trust and privacy. This paper introduces the GUARDIANPWA framework, a comprehensive approach to analyzing the PWA installation mechanism based on the CIA security principles (Confidentiality, Integrity, and Availability) and identifying areas where browser vendors fail to comply with these principles. Our study revealed 203 instances of non-compliance with security principles, highlighting how these irregularities in the PWA installation lifecycle can lead to potential violations of user privacy. For instance, in Firefox, PWAs installed in private mode incorrectly appear in normal mode, risking user confidentiality. Additionally, 29,465 PWAs are at risk because Samsung Internet does not display origins when PWAs navigate to third-party websites, undermining integrity. These findings were reported to browser vendors, leading to Firefox acknowledging four issues, resolving one, and planning to resolve two others. GUARDIANPWA supports developers by analyzing PWA manifest files for syntactic and semantic correctness, offering actionable recommendations, and helping to create PWAs that align with security best practices. By using GUARDIANPWA, developers and users can address critical security gaps and enhance compliance with CIA principles throughout the PWA installation lifecycle.
arXiv:2508.00472v2 Announce Type: replace Abstract: The tabular form constitutes the standard way of representing data in relational database systems and spreadsheets. But, similarly to other forms, tabular data suffers from class imbalance, a problem that causes serious performance degradation in a wide variety of machine learning tasks. One of the most effective solutions dictates the usage of Generative Adversarial Networks (GANs) in order to synthesize artificial data instances for the under-represented classes. Despite their good performance, none of the proposed GAN models takes into account the vector subspaces of the input samples in the real data space, leading to data generation in arbitrary locations. Moreover, the class labels are treated in the same manner as the other categorical variables during training, so conditional sampling by class is rendered less effective. To overcome these problems, this study presents ctdGAN, a conditional GAN for alleviating class imbalance in tabular datasets. Initially, ctdGAN executes a space partitioning step to assign cluster labels to the input samples. Subsequently, it utilizes these labels to synthesize samples via a novel probabilistic sampling strategy and a new loss function that penalizes both cluster and class mis-predictions. In this way, ctdGAN is trained to generate samples in subspaces that resemble those of the original data distribution. We also introduce several other improvements, including a simple, yet effective cluster-wise scaling technique that captures multiple feature modes without affecting data dimensionality. The exhaustive evaluation of ctdGAN with 14 imbalanced datasets demonstrated its superiority in generating high fidelity samples and improving classification accuracy.
arXiv:2508.02425v2 Announce Type: replace Abstract: In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments. Robots must analyze interactions with objects to ensure safety and facilitate meaningful workflows. One critical aspect is human/object detection, where the contacted object is identified. Past research introduced binary machine learning classifiers to distinguish between soft and hard objects. This study improves upon those results by evaluating three-class human/object detection models, offering more detailed contact analysis. A dataset was collected using the Franka Emika Panda robot manipulator, exploring preprocessing strategies for time-series analysis. Models including LSTM, GRU, and Transformers were trained on these datasets. The best-performing model achieved 91.11\% accuracy during real-time testing, demonstrating the feasibility of multi-class detection models. Additionally, a comparison of preprocessing strategies suggests a sliding window approach is optimal for this task.
arXiv:2512.16455v4 Announce Type: replace Abstract: The rapid growth of Artificial Intelligence and Machine Learning in scientific research has highlighted a gap between industry-standard MLOps tools and platforms, and the unique requirements of modern and Open Science, particularly regarding the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper presents AI4EOSC, a federated, open-source platform designed to operationalize the full AI/ML lifecycle within the European Open Science Cloud (EOSC) ecosystem. Our methodology tackles the fragmentation of distributed research infrastructures by integrating a modular and distributed architecture comprising an AI development platform, a serverless AI-as-a-Service layer, and a federated orchestration model that is able to integrate heterogeneous compute and storage resources from distributed e-Infrastructures. AI4EOSC also introduces a ``FAIR-by-design'' approach that enforces metadata standardization (via MLDCAT-AP) and W3C PROV-compliant provenance tracking through a platform-integrated CI/CD pipeline. AI4EOSC added value is demonstrated through the delivery of a diverse set of community installations, showing consistent and seamless deployment across heterogeneous cloud providers. These installations are validated by a set of scientific cases, showing how our work reduces the manual burden on researchers while ensuring high levels of reproducibility and interoperability and providing an unified environment for development, training, and production of AI/ML models in the EOSC.
arXiv:2508.02923v3 Announce Type: replace Abstract: Maximum A Posteriori (MAP) estimation is a cornerstone framework for blind inverse problems, where an image and a forward operator are jointly estimated as the maximizers of a posterior distribution. In applications such as blind deblurring, this principle is used to recover sharp images from degraded observations. In this paper, we analyze the recovery guarantees of MAP-based methods by adopting a \emph{Morse--Bott framework}. We model the image potential as a Morse--Bott function, where natural images are modeled as residing locally on a critical submanifold. This means that while the potential is locally flat along the ``natural'' directions of the image manifold, it is strictly convex in the directions normal to it. We demonstrate that this Morse--Bott hypothesis aligns with the structural properties of state-of-the-art learned priors, a finding we validate through an experimental analysis of the potential landscape and its Hessian spectrum. Our theoretical results show that, in a neighborhood of the ground-truth image and operator, the posterior admits local minimizers that are stable both with respect to initialization (gradient descents converge to the same minimizer) and to small perturbations of the data (solutions vary smoothly with the observations). This local stability potentially provides a theoretical justification for the empirical success of well designed gradient-based optimization in these settings. However, we also demonstrate that this local stability is a \textbf{local} property: the ``blurry trap'', well-known for sparse priors in blind deconvolution, persists even with state-of-the-art learned priors. Our findings demonstrate that the failure of MAP in blind deconvolution is not a limitation of prior quality, but an intrinsic characteristic of the landscape. We conclude that successful recovery depends on strategic initialization around favorable local minima.
arXiv:2509.20848v2 Announce Type: replace Abstract: In the classic point location problem, one is given an arbitrary dataset $X \subset \mathbb{R}^d$ of $n$ points with query access to an unknown halfspace $f : \mathbb{R}^d \to \{0,1\}$, and the goal is to learn the label of every point in $X$. This problem is extremely well-studied and a nearly-optimal $\widetilde{O}(d \log n)$ query algorithm is known due to Hopkins-Kane-Lovett-Mahajan (FOCS 2020). However, their algorithm is granted the power to query arbitrary points outside of $X$ (point synthesis), and in fact without this power there is an $\Omega(n)$ query lower bound due to Dasgupta (NeurIPS 2004). In this work our goal is to design efficient algorithms for learning halfspaces without point synthesis. To circumvent the $\Omega(n)$ lower bound, we consider learning halfspaces whose normal vectors come from a set of size $D$, and show tight bounds of $\Theta(D + \log n)$. As a corollary, we obtain an optimal $O(d + \log n)$ query deterministic learner for axis-aligned halfspaces, closing a previous gap of $O(d \log n)$ vs. $\Omega(d + \log n)$. In fact, our algorithm solves the more general problem of learning a Boolean function $f$ over $n$ elements which is monotone under at least one of $D$ provided orderings. Our technical insight is to exploit the structure in these orderings to perform a binary search in parallel rather than considering each ordering sequentially, and we believe our approach may be of broader interest. Furthermore, we use our exact learning algorithm to obtain nearly optimal algorithms for PAC-learning. We show that $O(\min(D + \log(1/\varepsilon), 1/\varepsilon) \cdot \log D)$ queries suffice to learn $f$ within error $\varepsilon$, even in a setting when $f$ can be adversarially corrupted on a $c\varepsilon$-fraction of points, for a sufficiently small constant $c$. This bound is optimal up to a $\log D$ factor, including in the realizable setting.
arXiv:2508.06720v3 Announce Type: replace Abstract: The primary limitation for the application of alchemical free energy methods to a wider variety of complex molecular systems is achieving reasonable sampling. Flexible binding complexes often have high free energy barriers, which require prohibitively long simulations or carefully tuned enhanced sampling methods in order to gather sufficient uncorrelated samples to obtain reliable free energy estimates. An example of such a flexible system is the complex formed between FabB, an elongating \b{eta}-ketoacyl-acyl carrier protein (ACP) synthase (KS) from Escherichia coli, and ACP, which carries acyl chains of varying lengths. Previous experimental evidence suggests that growing acyl chains can bind to at least two pockets in FabB. With the multiple topology replica exchange of expanded ensemble (MT-REXEE) enhanced sampling approach, we can obtain highly efficient sampling of both pockets by adaptively growing and shrinking the chains in the simulation ensemble, allowing each simulation to visit chain lengths where transitions between the pockets occur. This enables unbiased sampling of alternate configurational states for large complex systems without prior pocket definitions, as collective-variable based enhanced sampling methods would require. Using the new swapping approach gives significantly enhanced sampling even for this simpler problem, as demonstrated by faster convergence of free energy estimates of relative binding affinity between kinetically separated binding pockets. This case study demonstrates the utility of MT-REXEE and its open-source implementation for systems that feature high free energy barriers for a subset of ligands of interest, demonstrating a valuable addition to the existing stable of enhanced sampling methods.
arXiv:2508.12435v2 Announce Type: replace Abstract: While gesture recognition using vision or robot skins is an active research area in Human-Robot Collaboration (HRC), this paper explores deep learning methods relying solely on a robot's built-in joint sensors, eliminating the need for external sensors. We evaluated various convolutional neural network (CNN) architectures and collected a dataset to study the impact of data representation and model architecture on the recognition accuracy. Our results show that spectrogram-based representations significantly improve accuracy, while model architecture plays a smaller role. We also tested generalization to new robot poses, where spectrogram-based models performed better. Implemented on a Franka Emika Research robot, two of our methods, STFT2DCNN and STT3DCNN, achieved over 95% accuracy in contact detection and gesture classification. These findings demonstrate the feasibility of external-sensor-free tactile recognition and promote further research toward cost-effective, scalable solutions for HRC.
arXiv:2508.13084v2 Announce Type: replace Abstract: A novel long-lived distributed problem, called Team Formation (TF), is introduced together with a message- and time-efficient randomized algorithm. The problem is defined over the asynchronous model with a complete communication graph, using bounded size messages, where a certain fraction of the nodes may experience a generalized, strictly stronger, version of initial failures. The goal of a TF algorithm is to assemble tokens injected by the environment, in a distributed manner, into teams of size $\sigma$, where $\sigma$ is a parameter of the problem. The usefulness of TF is demonstrated by using it to derive efficient algorithms for many distributed problems. Specifically, we show that various (one-shot as well as long-lived) distributed problems reduce to TF. This includes well-known (and extensively studied) distributed problems such as several versions of leader election and threshold detection. For example, we are the first to break the linear message complexity bound for asynchronous implicit leader election. We also improve the time complexity of message-optimal algorithms for asynchronous explicit leader election. Other distributed problems that reduce to TF are new ones, including matching players in online gaming platforms, a generalization of gathering, constructing a perfect matching in an induced subgraph of the complete graph, quorum sensing in message-passing networks, and more. To complement our positive contribution, we establish a tight lower bound on the message complexity of TF algorithms.
arXiv:2508.14483v4 Announce Type: replace Abstract: We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional fine-tuning of such controllable pipelines frequently suffers from distribution drift due to limitations in imperfect multimodal alignment, resulting in compromised texture realism and temporal coherence. To tackle this challenge, we propose a concept distillation training strategy that utilizes the pretrained T2V model to synthesize training samples with embedded textual concepts, thereby distilling its conceptual understanding to preserve texture and temporal quality. To enhance generation controllability, we redesign the control architecture with two key components: 1) a control feature projector that filters degradation artifacts from input video latents to minimize their propagation through the generation pipeline, and 2) a new ControlNet connector employing a dual-branch design. This connector synergistically combines MLP-based feature mapping with cross-attention mechanism for dynamic control feature retrieval, enabling both content preservation and adaptive control signal modulation. Extensive experiments show that Vivid-VR performs favorably against existing approaches on both synthetic and real-world benchmarks, as well as AIGC videos, achieving impressive texture realism, visual vividness, and temporal consistency. The codes and checkpoints are publicly available at https://github.com/csbhr/Vivid-VR.
arXiv:2601.10542v3 Announce Type: replace Abstract: Certified deletion allows Alice to outsource data to Bob and, at a later time, obtain a verifiable guarantee that the file has been irreversibly deleted at her request. This functionality, while impossible using classical information alone, can be achieved using quantum information. Existing approaches rely either on one-time pad (OTP) encryption or on computational hardness assumptions that may be vulnerable to future advances in classical or quantum computing. In this work, we introduce and formalize hybrid encryption with certified deletion in the preprocessing model (pHE-CD) and propose two constructions. Each construction composes an information-theoretic key encapsulation mechanism (iKEM) with a data encapsulation mechanism that provides certified deletion (DEM-CD) security, offering different security guarantees depending on the properties of DEM-CD. When DEM-CD is one-time information-theoretically secure, the composition provides information-theoretic security for both encryption and certified deletion. When DEM-CD is computationally secure, the composed construction provides computationally secure (post-quantum) encryption and everlasting certified deletion, where confidentiality is computational until the deletion certificate is successfully verified. After successful verification, confidentiality becomes unconditional. That is, successful verification of the deletion certificate guarantees that the data has been removed information-theoretically from the adversary's view. Both pHE-CD constructions support the encryption of arbitrarily long messages. Construction 2 is key-efficient and uses a DEM-CD built from quantum coding and AES, providing quantum-safe security for encryption. We conclude by discussing the implications of our results and directions for future research.
arXiv:2601.15251v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved impressive proficiency in basic arithmetic, rivaling human-level performance on standard numerical tasks. However, little attention has been given to how these models perform when numerical expressions deviate from the prevailing conventions present in their training corpora. In this work, we investigate numerical reasoning across a wide range of numeral scripts and formats. We show that LLM accuracy drops substantially when numerical inputs are rendered in underrepresented scripts or formats, despite the underlying mathematical reasoning being identical. We further demonstrate that targeted prompting strategies, such as few-shot prompting and explicit numeral mapping, can greatly narrow this gap. Our findings highlight an overlooked challenge in multilingual numerical reasoning and provide actionable insights for working with LLMs to reliably interpret, manipulate, and generate numbers across diverse numeral scripts and formatting styles.
arXiv:2510.02308v2 Announce Type: replace Abstract: Estimating the tangent spaces of a data manifold is a fundamental problem in geometric data analysis. The standard approach, Local Principal Component Analysis (LPCA), struggles in high-noise setting due to a critical trade-off in choosing the neighborhood size. Selecting an optimal size requires prior knowledge of the geometric and noise characteristics of the data that are often unavailable. In this paper, we propose a spectral method, Laplacian Eigenvector Gradient Orthogonalization (LEGO), that utilizes the global structure of the data to guide local tangent space estimation. Instead of relying solely on local neighborhoods, LEGO estimates the tangent space at each data point by orthogonalizing the gradients of low-frequency eigenvectors of the graph Laplacian. We provide two theoretical justifications of our method. First, a differential geometric analysis on the tubular neighborhood of a manifold shows that gradients of the low-frequency Neumann eigenfunctions of the tube align closely with the manifold's tangent bundle, while an eigenfunction with high gradient in directions orthogonal to the manifold lie deeper in the spectrum. Second, a random matrix theoretic analysis also demonstrates that low-frequency eigenvectors are robust to sub-Gaussian noise. These results allow us to derive the asymptotic scaling and stability of the estimated eigenvector gradients. Numerical experiments demonstrate that LEGO yields tangent space estimates that are significantly more robust to noise than those from LPCA, resulting in marked improvements in downstream tasks such as manifold learning, boundary detection, and local intrinsic dimension estimation.
arXiv:2510.08611v2 Announce Type: replace Abstract: Anthropogenic greenhouse gas (GHG) emissions vary spatially with development patterns, climate, economic structure, and energy systems. Using Vulcan v4.0 fossil-fuel CO2 (FFCO2) data for the United States at 1-km resolution, this study examines how land use and infrastructure shape emissions at local and metropolitan scales. I combine doubly robust Bayesian Additive Regression Tree estimators with multi-treatment spatial regression models to identify local and spillover effects by sector. A key methodological contribution is treating transportation emissions as production-based, capturing infrastructure carbon burden rather than household-attributed travel demand. Results show strong scale dependence and spatial interaction: in the preferred heteroscedasticity-robust SLX+SEM model with a 10-km distance band, residual spatial autocorrelation declines substantially. Local roadway design is a strong negative predictor of transportation FFCO2, while neighbouring land use diversity exceeds local diversity. In residential sectors, higher local density is consistently associated with lower per-capita emissions. These findings support coordinated multi-scale mitigation policy in the United States.
arXiv:2510.09278v2 Announce Type: replace Abstract: Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency. Existing solutions to supervise reasoning, such as large-scale Process Reward Models (PRMs), are prohibitively expensive. To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using only a small, general-purpose LLM. CLARity integrates a consistency-aware reward mechanism with a 2-stage refine-then-monitor training pipeline to enhance reasoning consistency, and a dynamic data reformulation strategy to to better exploit limited data. Experiments demonstrate that CLARity improves response consistency by 16.5% and accuracy by 7.5% over baselines. Human evaluations further confirm holistic improvements in coherence and professionalism. Thus, CLARity offers a generalizable solution that enables smaller models to effectively guide expert models by reasoning consistency. Our code is open sourced at: https://github.com/Infinite-set/CLARity
arXiv:2510.09484v3 Announce Type: replace Abstract: Limited-Area Models (LAMs) enable weather forecasting over regional domains at higher resolutions than what is computationally feasible for global models. At such high resolutions, machine learning approaches for weather prediction increasingly rely on ensemble methods to produce probabilistic forecasts. However, existing machine learning LAMs are not scalable due to relying on computationally costly diffusion models or inefficient graph neural networks. We tackle this by introducing a new hybrid CNN/GNN architecture, tailored to the LAM weather forecasting problem. Using this architecture, we construct the DET-LAM deterministic model, producing LAM forecasts both more efficiently and accurately than its graph-based competitor. We then tackle the ensemble forecasting problem, by using this architecture as a backbone for the generative model CRPS-LAM. CRPS-LAM is trained using a Continuous Ranked Probability Score (CRPS) objective, enabling efficient training and sampling in a single forward pass. This yields a speedup of $\approx \times 39$ compared to diffusion-based baselines. We evaluate our approach on regional domains in northern Europe, demonstrating that CRPS-LAM produces skillful and well-calibrated forecasts across a range of atmospheric variables.
arXiv:2601.16172v3 Announce Type: replace Abstract: RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d.\ sampling budget from $k{=}32$ to $k{=}64$ produces zero additional solved theorems (42/244 in both cases). A fixed schedule of 15 tactic skeletons breaks this plateau and recovers a $+45%$ relative improvement at $k{=}16$ (mean $\Delta = +12.3 \pm 4.2$ theorems across $n{=}3$ seeds, sign preserved in every seed). A controlled diversity ablation rules out the prompt-diversity confound: tactic skeletons help, paraphrases match the baseline, and irrelevant Lean comments actively degrade. A leave-one-out formalization-difficulty stratification reveals a structural-content gradient across the three perturbations. The phenomenon is RL-specific: V1.5-Base proves zero theorems regardless of intervention, identifying RL as the stage that creates the proof capability which subsequently collapses; extending to two additional 7B Lean provers, RL-trained DeepSeek-Prover-V2-7B contributes $+3$ frontier solves no i.i.d. baseline can reach despite a flat aggregate, while SFT-trained Goedel-Prover does not ( $-10.0$ $\pm 4.4$ theorems, $n{=}3$, sign preserved every seed). Inference-time structural diversity is a cheap, complementary axis for RL-trained provers, orthogonal to scaling model size or training compute.
arXiv:2601.21864v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with biased behavior; however, such approaches are often brittle, weakly generalizable, data-inefficient, and prone to degrading general capability. We propose \textbf{KnowBias}, a lightweight and conceptually distinct framework that mitigates bias by strengthening, rather than suppressing, neurons encoding bias-knowledge. KnowBias identifies neurons encoding bias knowledge using a small set of bias-knowledge questions via attribution-based analysis, and selectively enhances them at inference time. This design enables strong debiasing while preserving general capabilities, generalizes across bias types and demographics, and is highly data efficient, requiring only a handful of simple yes/no questions and no retraining. Experiments across multiple benchmarks and LLMs demonstrate consistent state-of-the-art debiasing performance with minimal utility degradation. Data and code are available at https://github.com/JP-25/KnowBias.