Given Wikipedia's role as a trusted source of high-quality, reliable content, concerns are growing about the proliferation of low-quality machine-generated text (MGT) produced by large language models (LLMs) on its platform. Reliable detection of MGT is therefore essential. However, existing work primarily evaluates MGT detectors on generic generation tasks rather than on tasks more commonly performed by Wikipedia editors. This misalignment can lead to poor generalisability when applied in real-world Wikipedia contexts. We introduce WETBench, a multilingual, multi-generator, and task-specific benchmark for MGT detection. We define three editing tasks, empirically grounded in Wikipedia editors' perceived use cases for LLM-assisted editing: Paragraph Writing, Summarisation, and Text Style Transfer, which we implement using two new datasets across three languages. For each writing task, we evaluate three prompts, generate MGT across multiple generators using the best-performing prompt, and benchmark diverse detectors. We find that, across settings, training-based detectors achieve an average accuracy of 78%, while zero-shot detectors average 58%. These results show that detectors struggle with MGT in realistic generation scenarios and underscore the importance of evaluating such models on diverse, task-specific data to assess their reliability in editor-driven contexts.

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work linearized the softmax operation, resulting in powerful recurrent neural network (RNN) models with constant memory and compute costs such as DeltaNet, Mamba or xLSTM. These models can be unified by noting that their recurrent layer dynamics can all be derived from an in-context regression objective, approximately optimized through an online learning rule. Here, we join this line of work and introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer (von Oswald et al., 2024), which could only run sequentially in time and was therefore not scalable. This layer again stems from an in-context loss, but which is now minimized to optimality at every time point using a fast conjugate gradient solver. Through an extensive suite of experiments study up to the billion-parameter scale, we show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs, especially on tasks requiring long context understanding. This performance gain comes at the cost of additional flops spent during inference time. Our results are therefore intriguingly related to recent trends of increasing test-time compute to improve performance -- here by spending compute to solve sequential optimization problems within the neural network itself.

Compound flooding, driven by nonlinear interactions between multiple hydrometeorological factors, poses a significant challenge to hazard prevention. Existing forecasting approaches, whether physics-based or data-driven, often emphasize temporal patterns while underexploring how multiple interacting factors jointly shape flood dynamics. To address this problem, we conduct a large-scale data-driven analysis of compound flooding in South Florida, a typical area for compound flooding, by integrating tidal conditions, rainfall, groundwater stage, and human water management activities. Our analysis reveals three key findings: (i) models that capture temporal dynamics alone fail to represent multi-factor interactions during compound events; (ii) subsurface saturation, as reflected by groundwater levels, emerges as a dominant predictor of flood severity, often outweighing immediate rainfall intensity in this porous coastal region; and (iii) the spatial state of surrounding monitoring stations within a finite effective radius provides critical causal context for flooding, while extending temporal history yields diminishing returns during extreme events. These findings suggest that compound flooding is governed more by spatially coupled system states than by long-term temporal dependencies, challenging rain-centric and sequence-dominated forecasting paradigms. By framing data-driven models as tools for scientific inquiry rather than prediction alone, this study offers new insights into the mechanisms of compound flooding and informs the design of more physically grounded early-warning systems for coastal environments. Our dataset and code are publicly available at https://github.com/AslanDing/SFBench.

Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effortlessly process many originally exhausting tasks -- e.g., digesting a long-form document to find answers vs. directly asking an LLM about it. However, existing real-task-based long-context evaluation benchmarks have two major shortcomings. First, benchmarks like LongBench often do not provide proper metrics to separate long-context performance from the model's baseline ability, making cross-model comparison unclear. Second, such benchmarks are usually constructed with fixed input lengths, which limits their applicability across different models and fails to reveal when a model begins to break down. To address these issues, we introduce a length-controllable long-context benchmark and a novel metric that disentangles baseline knowledge from true long-context capabilities. Experiments demonstrate the superiority of our approach in effectively evaluating LLMs.

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient long-context capacity, motivated by empirical observations such as (1) higher context window length often leads to stronger reasoning performance, and (2) failed reasoning cases resemble failed long-context cases. To test this hypothesis, we examine whether enhancing a model's long-context ability before Supervised Fine-Tuning (SFT) leads to improved reasoning performance. Specifically, we compared models with identical architectures and fine-tuning data but varying levels of long-context capacity. Our results reveal a consistent trend: models with stronger long-context capacity achieve significantly higher accuracy on reasoning benchmarks after SFT. Notably, these gains persist even on tasks with short input lengths, indicating that long-context training offers generalizable benefits for reasoning performance. These findings suggest that long-context modeling is not just essential for processing lengthy inputs, but also serves as a critical foundation for reasoning. We advocate for treating long-context capacity as a first-class objective in the design of future language models.

Multi-step reasoning is essential for large language models (LLMs), yet multilingual performance remains challenging. While Chain-of-Thought (CoT) prompting improves reasoning, it struggles with non-English languages due to the entanglement of reasoning and execution. Program-of-Thought (PoT) prompting separates reasoning from execution, offering a promising alternative but shifting the challenge to generating programs from non-English questions. We propose a framework to evaluate PoT by separating multilingual reasoning from code execution to examine (i) the impact of fine-tuning on question-reasoning alignment and (ii) how reasoning quality affects answer correctness. Our findings demonstrate that PoT fine-tuning substantially enhances multilingual reasoning, outperforming CoT fine-tuned models. We further demonstrate a strong correlation between reasoning quality (measured through code quality) and answer accuracy, highlighting its potential as a test-time performance improvement heuristic.

Time-series forecasting is a critical task in various business domains, but it remains inherently challenging. Typically, large forecasting models are trained in a single, resource-intensive run. Once training is completed, a natural question arises:~\emph{is there still potential for meaningful improvement in the model's performance?} Motivated by techniques from boosting, we introduce the concept of~\emph{post-training corrections}. This approach enhances a trained forecaster by sequentially applying a carefully selected set of corrections to its predictions. Our method offers a lightweight, model-agnostic, and scalable strategy to improve forecasting performance in practical settings. We provide theoretical foundations for the approach, starting with the affine correction case, and analyze the expected performance gains and computational costs in more general settings. Across a range of benchmark datasets, our method consistently delivers up to a $30\%$ improvement in forecasting accuracy over existing state-of-the-art models, with minimal computational overhead.

Molecular generation plays an important role in drug discovery and materials science, especially in data-scarce scenarios where traditional generative models often struggle to achieve satisfactory conditional generalization. To address this challenge, we propose MetaMolGen, a first-order meta-learning-based molecular generator designed for few-shot and property-conditioned molecular generation. MetaMolGen standardizes the distribution of graph motifs by mapping them to a normalized latent space, and employs a lightweight autoregressive sequence model to generate SMILES sequences that faithfully reflect the underlying molecular structure. In addition, it supports conditional generation of molecules with target properties through a learnable property projector integrated into the generative process.Experimental results demonstrate that MetaMolGen consistently generates valid and diverse SMILES sequences under low-data regimes, outperforming conventional baselines. This highlights its advantage in fast adaptation and efficient conditional generation for practical molecular design.

Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free framework that enables large reasoning models to guide smaller ones during inference at the reasoning level, distinct from speculative decoding, which operates at the token level. Our approach is based on two observations: (1) reasoning-supportive tokens such as "wait" frequently appear after structural delimiters like "\n\n", serving as signals for reflection or continuation; and (2) larger models exhibit stronger control over reflective behavior, reducing unnecessary backtracking while improving reasoning quality. By strategically delegating reflective steps to a more capable model, our method significantly boosts the reasoning accuracy of reasoning models while shortening their output. With the assistance of the 32B reasoning model, the 1.5B model's accuracy on MATH500 increases from 83.2% to 89.4%, marking a substantial improvement of 6.2%. Simultaneously, the average output length is reduced from 5439 tokens to 4583 tokens, representing a 15.7% decrease. Moreover, when applied to a non-reasoning model (Qwen-2.5-7B-Instruct), our framework boosts its accuracy from 74.0% to 81.8% on the same benchmark, achieving a relative improvement of 7.8%.

Value function factorization is widely used in cooperative multi-agent reinforcement learning (MARL). Existing approaches often impose monotonicity constraints between the joint action value and individual action values to enable decentralized execution. However, such constraints limit the expressiveness of value factorization, restricting the range of joint action values that can be represented and hindering the learning of optimal policies. To address this, we propose Potentially Optimal Joint Actions Weighting (POW), a method that ensures optimal policy recovery where existing approximate weighting strategies may fail. POW iteratively identifies potentially optimal joint actions and assigns them higher training weights through a theoretically grounded iterative weighted training process. We prove that this mechanism guarantees recovery of the true optimal policy, overcoming the limitations of prior heuristic weighting strategies. POW is architecture-agnostic and can be seamlessly integrated into existing value factorization algorithms. Extensive experiments on matrix games, difficulty-enhanced predator-prey tasks, SMAC, SMACv2, and a highway-env intersection scenario show that POW substantially improves stability and consistently surpasses state-of-the-art value-based MARL methods.

Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction. This requires a scalar prediction as in binary classification, whereas a multiclass probabilistic prediction is a discrete probability distribution, living on a multidimensional simplex. In such a multiclass setting the Shapley values are typically computed separately on each class in a one-vs-rest manner, ignoring the compositional nature of the output distribution. In this paper, we introduce Shapley compositions as a well-founded way to properly explain a multiclass probabilistic prediction, using the Aitchison geometry from compositional data analysis. We prove that the Shapley composition is the unique quantity satisfying linearity, symmetry and efficiency on the Aitchison simplex, extending the corresponding axiomatic properties of the standard Shapley value. We demonstrate this proper multiclass treatment in a range of scenarios.

The utility of large language models (LLMs) depends heavily on the quality and quantity of their training data. Many organizations possess large data corpora that could be leveraged to train or fine-tune LLMs tailored to their specific needs. However, these datasets often come with access restrictions that are based on user privileges and enforced by access control mechanisms. Training LLMs on such datasets could result in exposure of sensitive information to unauthorized users. A straightforward approach for preventing such exposure is to train a separate model for each access level. This, however, may result in low utility models due to the limited amount of training data per model compared to the amount in the entire organizational corpus. Another approach is to train a single LLM on all the data while limiting the exposure of unauthorized information. However, current exposure-limiting methods for LLMs are ineffective for access-controlled data, where sensitive information appears frequently across many training examples. We propose DOMBA - double model balancing - a simple approach for training and deploying LLMs that provides high utility and access-control functionality with security guarantees. DOMBA aggregates the probability distributions of two models, each trained on documents with (potentially many) different access levels, using a "min-bounded" average function (a function that is bounded by the smaller value, e.g., harmonic mean). A detailed mathematical analysis and extensive evaluation show that DOMBA safeguards restricted information while offering utility comparable to non-secure models.

In many fields, such as language acquisition, neuropsychology of language, the study of aging, and historical linguistics, corpora are used for estimating the diversity of grammatical structures that are produced during a period by an individual, community, or type of speakers. In these cases, treebanks are taken as representative samples of the syntactic structures that might be encountered. Generalizing the potential syntactic diversity from the structures documented in a small corpus requires careful extrapolation whose accuracy is constrained by the limited size of representative sub-corpora. In this article, I demonstrate -- theoretically, and empirically -- that a grammar's derivational entropy and the mean length of the utterances (MLU) it generates are fundamentally linked, giving rise to a new measure, the derivational entropy rate. The mean length of utterances becomes the most practical index of syntactic complexity; I demonstrate that MLU is not a mere proxy, but a fundamental measure of syntactic diversity. In combination with the new derivational entropy rate measure, it provides a theory-free assessment of grammatical complexity. The derivational entropy rate indexes the rate at which different grammatical annotation frameworks determine the grammatical complexity of treebanks. I introduce the Smoothed Induced Treebank Entropy (SITE) as a tool for estimating these measures accurately, even from very small treebanks. I conclude by discussing important implications of these results for both NLP and human language processing.

Remote sensing change detection based on a map reference and an up-to-date image boosts timely observation of the Earth's surface when earlier images are lacking for comparison. However, the semantic gap between high-level map categories and low-level image details hinders the extraction of homogeneous features for robust temporal association in change detection. Unlike conventional approaches that either compare pixel-level visual similarity or propagate segmentation errors, \textcolor{black}{we propose a novel framework, \underline{La}nguage-\underline{VI}sion \underline{D}iscriminator for d\underline{E}tecting changes, LaVIDE}, which bridges the semantic gap between high-level map categories and low-level image details using language as an intermediary. Specifically, we introduce {\it restricted prompt learning} to generate context-aware textual prompts that align map semantics with image content, and an {\it object-aware embedding enhancement} strategy to integrate object-level attributes (e.g., shape, boundary) into map representations. These components enable robust cross-modal alignment within a unified language-vision feature space. Extensive experiments on four benchmarks, DynamicEarthNet, HRSCD, BANDON, and SECOND, demonstrate that LaVIDE outperforms state-of-the-art methods by significant margins, achieving $18.4\%$ and $5.2\%$ improvements in IoU on multi-class and single-class change detection tasks, respectively. Our framework not only advances the accuracy of map-image change detection but also provides a practical solution for rapid map updating with minimal human intervention, promising broad impacts in urban planning, disaster assessment, and ecological conservation. Code and datasets are available at: https://github.com/ShuGuoJ/LAVIDE.git.

Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. Some of them involve fine-tuning a unique personalized LLM for each user, which is too expensive for widespread application. Alternative approaches introduce personalization information in a plug-and-play manner by retrieving the user's relevant historical texts as demonstrations. However, this retrieval-based strategy may break the continuity of the user history and fail to capture the user's overall styles and patterns, hence leading to sub-optimal performance. To address these challenges, we propose a novel personalized LLM model, PPlug. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module. By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their own parameters. Extensive experiments on various tasks in the language model personalization (LaMP) benchmark demonstrate that the proposed model significantly outperforms existing personalized LLM approaches.

Vision State Space Models (VSSMs), a novel architecture that combines the strengths of recurrent neural networks and latent variable models, have demonstrated remarkable performance in visual perception tasks by efficiently capturing long-range dependencies and modeling complex visual dynamics. However, their robustness under natural and adversarial perturbations remains a critical concern. In this work, we present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios, including occlusions, image structure, common corruptions, and adversarial attacks, and compare their performance to well-established architectures such as transformers and Convolutional Neural Networks. Furthermore, we investigate the resilience of VSSMs to object-background compositional changes on sophisticated benchmarks designed to test model performance in complex visual scenes. We also assess their robustness on object detection and segmentation tasks using corrupted datasets that mimic real-world scenarios. To gain a deeper understanding of VSSMs' adversarial robustness, we conduct a frequency-based analysis of adversarial attacks, evaluating their performance against low-frequency and high-frequency perturbations. Our findings highlight the strengths and limitations of VSSMs in handling complex visual corruptions, offering valuable insights for future research. Our code and models will be available at https://github.com/HashmatShadab/MambaRobustness.

Achieving rotational invariance in deep neural networks without data augmentation is a research hotspot. Intrinsic invariance enables features to capture targets' inherent properties, enhancing deep learning performance in visual tasks. Based on various types of non-learnable operators, this paper proposes a comprehensive set of convolution operations that are natually invariant to arbitrary rotations. Unlike most prior methods, these rotation-invariant convolutions (RIConvs) have the same number of learnable parameters and a similar computational process as standard convolutions, making them interchangeable. Using the MNIST-Rot dataset, we validate their invariance across rotation angles and compare them with previous rotation-invariant CNNs, where two gradient-based RIConvs achieve state-of-the-art results. Then, we integrate RIConvs with classic CNN backbones and evaluate them on texture recognition, aircraft type recognition, and remote sensing image classification tasks. Results show that RIConvs significantly improve accuracy, particularly with limited training data, and enhance performance even with data augmentation.

Hybrid track/wheel-legged robots combine the advantages of wheel-based and leg-based locomotion, granting adaptability across varied terrains through efficient transitions between rolling and walking modes. However, automating these transitions remains a significant challenge. In this paper, we introduce a method designed for autonomous mode transition in a quadruped hybrid robot with a track/wheel-legged configuration, especially during step negotiation. Our approach hinges on a decision-making mechanism that evaluates the energy efficiency of both locomotion modes using a proposed energy-based criterion. To guarantee a smooth negotiation of steps, we incorporate two climbing gaits designated for the assessment of energy usage in walking locomotion. Simulation results validate the method's effectiveness, showing successful autonomous transitions across steps of diverse heights. Our suggested approach has universal applicability and can be modified to suit other hybrid robots of similar mechanical configuration, provided their locomotion energy performance is studied beforehand.

In this work, we propose ESG, a pipeline for high-quality entity segmentation and grounding supported by a new dataset EntitySeg. At first, the proposed dataset naming EntitySeg contains images spanning various image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Then, the ESG mainly consists of two modules: CropFormer for high-quality entity segmentation whereas GELLA for accurate noun extraction from sentences and semantic matching between language and visual regions. Unlike existing grounding methods that jointly train a segmentation and a large language model, ESG adopts a two-stage decoupled design, preserving high-quality masks and grounding robustness without the trade-offs often introduced by joint training. CropFormer ensures high-quality entity segmentation results, which can then be encoded into the GELLA model for effective grounding. Extensive experimental results demonstrate the effectiveness of our proposed pipeline across five tasks, including entity segmentation, panoptic segmentation, open-vocabulary segmentation, referring segmentation, and panoptic localized narratives. Furthermore, GELLA module of ESG pipeline is highly flexible and capable of processing mask inputs from any segmentation framework, thanks to its lightweight colormap/vision encoder, language/mask decoder, and association module. The entity segmentation dataset and grounding code will be released at https://github.com/qqlu/Entity.

As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this paper, we introduce the paradigm of super policy learning that takes advantage of Human-AI interaction for data driven sequential decision making. This approach utilizes the observed action, either from AI or humans, as input for achieving a stronger oracle in policy learning for the decision maker (humans or AI). In the decision process with unmeasured confounding, the actions taken by past agents can offer valuable insights into undisclosed information. By including this information for the policy search in a novel and legitimate manner, the proposed super policy learning will yield a super-policy that is guaranteed to outperform both the standard optimal policy and the behavior one (e.g., past agents' actions). We call this stronger oracle a blessing from human-AI interaction. Furthermore, to address the issue of unmeasured confounding in finding super-policies using the batch data, a number of nonparametric and causal identifications are established under the framework of proximal causal inference. Building upon on these novel identification results, we develop several super-policy learning algorithms and systematically study their theoretical properties such as finite-sample regret guarantee. Finally, we illustrate the effectiveness of our proposal through extensive simulations and real-world applications.

Preserving data privacy is an important topic in structural data management and data mining. However, the issue of privacy leakage in distributed causal structure learning is a persistent challenge, especially in cases where data transmission and computation are required. In this paper, we propose a method based on fully homomorphic encryption (FHE) that performs calculations on ciphertexts, keeping data encrypted in transition and computation. Nevertheless, adopting FHE to causal structure learning is challenging due to the high computation cost and limited support on division as well as logarithm operations in FHE. To tackle this challenge, we propose a series of novel techniques including (i) circuit simplification for better efficiency, (ii) approximation of division and logarithm through Newton-Raphson Reciprocal and Taylor expansion, and (iii) a batching technique with SIMD-acceleration to enhance the whole learning process. Additionally, our method can be easily extended beyond FHE by demonstration of its portability to support differential privacy. Empirical results show that our method achieves high consistency and comparable causal structure with the plaintext version in the datasets tested. Last, our method is efficient and practical to complete learning causal structures in tens of minutes even under the privacy protection of FHE.

After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS remains challenging and can often reduce the appearance rendering quality. In this work, we show that 3DGS in its default form is inheritedly unsuited to represent texture and geometry at the same time, by training with complete ground-truth texture and geometry information. We also propose a simple solution by applying a single additional geometry opacity parameter to each splat, together with an optional transparency-curated optimization pipeline. Our experiments, both with ground-truth and vision foundation model geometric input, show that this change leads to improved rendering and geometry performance on a wide variety of dataset, and especially complex scenes with transparent objects benefit significantly from our method.

We present in this paper a framework for the identification of control-affine reduced-order models (ROMs). The proposed method utilizes autoencoders (AEs) to transform the high-dimensional states, and potentially the high-dimensional inputs, into reduced latent ones suitable for control-affine state-space dynamics. This is achieved by simultaneous training of the AE and the state-space model. In addition, we extend the discrete ROM formulation to a sequence-based model, which processes state and input histories to improve prediction accuracy while preserving the control-affine structure. We motivate our framework by applying feedback linearization to the derived models, and we present guidelines for its efficient use. The proposed framework is assessed on two numerical examples and its performance is compared to a baseline model, where the AE identifies a latent space with linear state-space dynamics. The assessment involves evaluating the prediction accuracy of the ROM on test data and its effectiveness in controlling the system to a desired state or trajectory.

When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recovery\_feedback.suggestions[] payload sufficient for the agent to repair the request and retry without external reasoning. On a leak-audited pilot ($N{=}30$ per cell, 3 LLMs, 10 adversarial tasks), structured suggestions lift task-completion rate by $+36.7$--$40.0$pp over plain-English diagnoses on Anthropic models (Fisher's exact $p \le 0.0022$), at $1.8$--$2.2\times$ better per-success token efficiency. The lift is not significant on gpt-4o-mini ($p{=}0.435$); a second-domain replication on a billing API confirms the pattern. The comparison only holds after auditing two undocumented classes of answer leakage in LLM benchmarks. We shipaudit\_prompt\_leakage.py as reusable CI infrastructure. Code and data: https://github.com/arquicanedo/self-reflective-apis.

With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-preserving inference methods sacrifice either utility or efficiency, and often require model-specific modifications that limit their compatibility. In this paper, we propose SharedRequest, a model-agnostic framework for privacy-preserving LLM inference that reformulates privacy protection at the batch level rather than the individual-prompt level. The key idea is to obscure sensitive information by mixing original prompts with noisy variants, while grouping semantically equivalent instructions to amortize the inference cost over a large batch of queries with minimal impact on LLM response quality. This design is independent of the LLM architecture, requiring no access to model parameters or architectural modification. Empirical results demonstrate that SharedRequest achieves over $20\%$ higher utility compared to prior differential privacy baselines, and its shared-prompt mechanism reduces query cost by up to $5\times$ compared to non-batched inference.

Although much is known about the physical danger of cycling situations, less is understood about the perceived danger of cycling. Furthermore, perception of danger may be filtered at a subconscious level and therefore difficult for one to self-report. To this end, these subconscious perceptions can be revealed through physiological metrics such as eye gaze. This paper explores the perceived safety of cycling in Oxford, United Kingdom and explores the ability of wearable eye tracking glasses to produce insights about the differences in perception under different environments and events. This paper finds that eye gaze patterns change between using bike lanes, car lanes and shared bus lanes, representing different cognitive challenges of each lane type. This paper presents that different intersections have significantly different eye gaze patterns which may have implications for cyclist stress. Finally, eye gaze patterns differ in the presence of events such as passes and pedestrians in the road compared to when cycling with no events. This paper draws conclusions on the benefits and limitations of using wearable eye trackers to estimate stress and cyclist workload.

AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles, artifacts and verification. Recent surveys map agents and LLMs for software engineering, but a study centered on the operational frameworks that turn these capabilities into process is missing. We ran a directed search of primary sources, with a functional inclusion criterion and traction measurement, and selected six frameworks: GitHub Spec Kit, OpenSpec, BMAD Method, Get Shit Done (GSD), Spec Kitty and Reversa. Each attacks AI development through a different path: spec-driven development in full and lightweight variants, agent-driven agile planning, context engineering over the agent, worktree isolation and review, and recovery of operational specifications from legacy systems. Our central contribution is a six-dimension process taxonomy: specification, context, roles, execution, validation and portability, with a scoring rubric that turns it into a replicable instrument. We apply it to the six frameworks and an out-of-sample case, Spec-Flow. Two results stand out. Among frameworks that already adopt some process there is convergence: the isolated prompt loses centrality, and persistent artifacts, work contracts, traceability and human review become mechanisms that reduce ambiguity and coordinate agents. And no framework strongly covers all six dimensions, exposing a structural trade-off between process depth and portability across agents. We also found recurring risks: drift between specification and code, excessive trust in generated artifacts, fragility of community extensions, platform dependence and a lack of benchmarks for the complete process. We close with a research agenda for empirical evaluation, focused on intermediate-quality metrics, context governance, installation security and reproducibility.

System-generated logs underpin security monitoring, yet their rigid template-based format hinders both automated analysis and human comprehension. We present NLLog (Natural-Language Log), a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences, pools them with term-frequency-inverse-document-frequency weighting, classifies sessions with tree ensembles, and back-projects evidence with TreeSHAP for analyst review. On Hadoop Distributed File System (HDFS) and Blue Gene/L (BGL) corpora, NLLog exceeds two reproduced matched-protocol baselines; across HDFS, BGL, and the AIT Alert Data Set, it sustains low false-positive rates with commodity-hardware latency suitable for security operations center triage. Coverage, sparse-versus-dense, faithfulness, and adversarial ablations show that fallback sufficiency is corpus-dependent, that an enrollment-time coverage check can surface refinement requirements before deployment, and that an auditable deterministic rewrite combined with lightweight dense encoding provides a measurable representation layer for log-anomaly detection and triage.

Consistency is an important property in dynamic submodular maximization and entails maintaining a near-optimal solution at all times, making only a small number of adjustments to the solution in each step. Prior work has explored this question for the insertion-only case, where the algorithm faces a stream of $n$ insertions, and has established lower and upper bounds for the cardinality-constrained version of the problem. We consider this question in the fully dynamic setting, where the stream of operations may contain both insertions and deletions. We develop a general framework for designing algorithms for this setting, and instantiate it to obtain the first constant-factor approximations with sublinear consistency. For cardinality constraints, we propose a $\frac 12 - O(\varepsilon)$ approximation that is $O\left(\frac{1}{\varepsilon^2}\right)$ consistent. For rank-$k$ matroid constraints, we construct a $\frac 14 - O(\varepsilon)$ approximation to the dynamic optimum that is $O\left(\frac{\log k}{\varepsilon^2}\right)$ consistent.

E-commerce platforms in emerging markets often operate with underdeveloped product catalogs that contain only category taxonomies but lack structured attribute schemas. This absence of fine-grained product attributes limits search capabilities -- preventing faceted filtering, degrading query understanding, and weakening semantic representations used by search systems. We present BEATS, a human-in-the-loop LLM framework for bootstrapping product attribute taxonomies entirely from scratch. Our approach extends a multi-stage LLM generation pipeline with two critical production stages: (1) proactive quality checking by model developers to filter erroneous outputs, and (2) human annotation by domain-expert local staff to validate generated attributes. The framework operates iteratively -- prompts at each generation stage are refined based on quality check observations and annotator feedback across successive rounds, progressively improving attribute quality. Once the attribute taxonomy is established, we employ LLMs to perform structured attribute tagging on individual product items, enriching their contextual representations. The enriched catalog directly benefits multiple components of the search system: enabling granular attribute-based filtering, providing structured features for ranking models, and improving semantic representations for dense retrieval. We validate the generated taxonomy by training dense retrieval models on attribute-enriched product data, demonstrating consistent improvements over baselines using original catalog information. Our system has been deployed at Rakuten Taiwan, enriching 9 major categories spanning 2,694 sub-categories with 67,277 generated attributes, and over 5.4 million products have been tagged with the generated attributes, with plans to enrich the entire product catalog.