Flight delays due to holding maneuvers are a critical and costly phenomenon in aviation, driven by the need to manage air traffic congestion and ensure safety. Holding maneuvers occur when aircraft are instructed to circle in designated airspace, often due to factors such as airport congestion, adverse weather, or air traffic control restrictions. This study models the prediction of flight delays due to holding maneuvers as a graph problem, leveraging advanced Graph Machine Learning (Graph ML) techniques to capture complex interdependencies in air traffic networks. Holding maneuvers, while crucial for safety, cause increased fuel usage, emissions, and passenger dissatisfaction, making accurate prediction essential for operational efficiency. Traditional machine learning models, typically using tabular data, often overlook spatial-temporal relations within air traffic data. To address this, we model the problem of predicting holding as edge feature prediction in a directed (multi)graph where we apply both CatBoost, enriched with graph features capturing network centrality and connectivity, and Graph Attention Networks (GATs), which excel in relational data contexts. Our results indicate that CatBoost outperforms GAT in this imbalanced dataset, effectively predicting holding events and offering interpretability through graph-based feature importance. Additionally, we discuss the model's potential operational impact through a web-based tool that allows users to simulate real-time delay predictions. This research underscores the viability of graph-based approaches for predictive analysis in aviation, with implications for enhancing fuel efficiency, reducing delays, and improving passenger experience.

Recent studies show that in supervised fine-tuning (SFT) of large language models (LLMs), data quality matters more than quantity. While most data cleaning methods concentrate on filtering entire samples, the quality of individual tokens within a sample can vary significantly. After pre-training, even in high-quality samples, patterns or phrases that are not task-related can be redundant, uninformative, or even harmful. Continuing to fine-tune on these patterns may offer limited benefit and even degrade downstream task performance. In this paper, we investigate token quality from a noisy-label perspective and propose a generic token cleaning pipeline for SFT tasks. Our method filters out uninformative tokens while preserving those carrying key task-specific information. Specifically, we first evaluate token quality by examining the influence of model updates on each token, then apply a threshold-based separation. The token influence can be measured in a single pass with a fixed reference model or iteratively with self-evolving reference models. The benefits and limitations of both methods are analyzed theoretically by error upper bounds. Extensive experiments show that our framework consistently improves downstream performance. Code is available at https://github.com/UCSC-REAL/TokenCleaning.

Designing stylized cinemagraphs is challenging due to the difficulty in customizing complex and expressive flow elements. To achieve intuitive and detailed control of the generated cinemagraphs, sketches provide a feasible solution to convey personalized design requirements beyond text inputs. In this paper, we propose Sketch2Cinemagraph, a sketch-guided framework that enables the conditional generation of stylized cinemagraphs from freehand sketches. Sketch2Cinemagraph adopts text prompts for initial landscape generation and provides sketch controls for both spatial and motion cues. The latent diffusion model first generates target stylized landscape images along with realistic versions. Then, a pre-trained object detection model obtains masks for the flow regions. We propose a latent motion diffusion model to estimate motion field in fluid regions of the generated landscape images. The input motion sketches serve as the conditions to control the generated motion fields in the masked fluid regions with the prompt. To synthesize cinemagraph frames, the pixels within fluid regions are warped to target locations at each timestep using a U-Net based frame generator. The results verified that Sketch2Cinemagraph can generate aesthetically appealing stylized cinemagraphs with continuous temporal flow from sketch inputs. We showcase the advantages of Sketch2Cinemagraph through qualitative and quantitative comparisons against the state-of-the-art approaches.

Foundation models like Vision-Language Models (VLMs) excel at common sense vision and language tasks such as visual question answering. However, they cannot yet directly solve complex, long-horizon robot manipulation problems requiring precise continuous reasoning. Task and Motion Planning (TAMP) systems can handle long-horizon reasoning through discrete-continuous hybrid search over parameterized skills, but rely on detailed environment models and cannot interpret novel human objectives, such as arbitrary natural language goals. We propose integrating VLMs into TAMP systems by having them generate discrete and continuous language-parameterized constraints that enable open-world reasoning. Specifically, we use VLMs to generate discrete action ordering constraints that constrain TAMP search over action sequences, and continuous constraints in the form of code that augments traditional TAMP manipulation constraints. Experiments show that our approach, OWL-TAMP, outperforms baselines relying solely on TAMP or VLMs across several long-horizon manipulation tasks specified directly in natural language. We additionally demonstrate that OWL-TAMP can be deployed with an off-the-shelf TAMP system to solve challenging manipulation tasks on real-world hardware.

This study focuses on incremental learning for image classification, exploring how to reduce catastrophic forgetting of all learned knowledge when access to old data is restricted. The challenge lies in balancing plasticity (learning new knowledge) and stability (retaining old knowledge). Based on whether the task identifier (task-ID) is available during testing, incremental learning is divided into task incremental learning (TIL) and class incremental learning (CIL). The TIL paradigm often uses multiple classifier heads, selecting the corresponding head based on the task-ID. Since the CIL paradigm cannot access task-ID, methods originally developed for TIL require explicit task-ID prediction to bridge this gap and enable their adaptation to the CIL paradigm. {In this study, a novel continual learning framework extends the TIL method for CIL by introducing out-of-distribution detection for task-ID prediction. Our framework utilizes task-specific Batch Normalization (BN) and task-specific classification heads to effectively adjust feature map distributions for each task, enhancing plasticity. With far fewer parameters than convolutional kernels, task-specific BN helps minimize parameter growth, preserving stability. Based on multiple task-specific classification heads, we introduce an ``unknow'' class for each head. During training, data from other tasks are mapped to this unknown class. During inference, the task-ID is predicted by selecting the classification head with the lowest probability assigned to the unknown class. Our method achieves state-of-the-art performance on two medical image datasets and two natural image datasets. The source code is available at https://github.com/z1968357787/mbn_ood_git_main.

Goal hijacking is a type of adversarial attack on Large Language Models (LLMs) where the objective is to manipulate the model into producing a specific, predetermined output, regardless of the user's original input. In goal hijacking, an attacker typically appends a carefully crafted malicious suffix to the user's prompt, which coerces the model into ignoring the user's original input and generating the target response. In this paper, we introduce a novel goal hijacking attack method called Pseudo-Conversation Injection, which leverages the weaknesses of LLMs in role identification within conversation contexts. Specifically, we construct the suffix by fabricating responses from the LLM to the user's initial prompt, followed by a prompt for a malicious new task. This leads the model to perceive the initial prompt and fabricated response as a completed conversation, thereby executing the new, falsified prompt. Following this approach, we propose three Pseudo-Conversation construction strategies: Targeted Pseudo-Conversation, Universal Pseudo-Conversation, and Robust Pseudo-Conversation. These strategies are designed to achieve effective goal hijacking across various scenarios. Our experiments, conducted on two mainstream LLM platforms including ChatGPT and Qwen, demonstrate that our proposed method significantly outperforms existing approaches in terms of attack effectiveness.

The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthroughs in combinatorial optimization and scientific discovery. We propose to extend this powerful combination to the control of dynamical systems, generating interpretable control policies capable of complex behaviors. With our novel method, we represent control policies as programs in standard languages like Python. We evaluate candidate controllers in simulation and evolve them using a pre-trained LLM. Unlike conventional learning-based control techniques, which rely on black-box neural networks to encode control policies, our approach enhances transparency and interpretability. We still take advantage of the power of large AI models, but only at the policy design phase, ensuring that all system components remain interpretable and easily verifiable at runtime. Additionally, the use of standard programming languages makes it straightforward for humans to finetune or adapt the controllers based on their expertise and intuition. We illustrate our method through its application to the synthesis of an interpretable control policy for the \textit{pendulum swing-up} and the \textit{ball in cup} tasks. We make the code available at https://github.com/muellerlab/synthesizing_interpretable_control_policies.git.

In this study, explainable machine learning techniques are applied to predict the toxicity of mussels in the Gulf of Trieste (Adriatic Sea) caused by harmful algal blooms. By analysing a newly created 28-year dataset containing records of toxic phytoplankton in mussel farming areas and toxin concentrations in mussels (Mytilus galloprovincialis), we train and evaluate the performance of ML models to accurately predict diarrhetic shellfish poisoning (DSP) events. The random forest model provided the best prediction of positive toxicity results based on the F1 score. Explainability methods such as permutation importance and SHAP identified key species (Dinophysis fortii and D. caudata) and environmental factors (salinity, river discharge and precipitation) as the best predictors of DSP outbreaks. These findings are important for improving early warning systems and supporting sustainable aquaculture practices.

This paper argues that large language models have a valuable scientific role to play in serving as scientific models of public languages. Linguistic study should not only be concerned with the cognitive processes behind linguistic competence, but also with language understood as an external, social entity. Once this is recognized, the value of large language models as scientific models becomes clear. This paper defends the position against a number of arguments to the effect that language models provide no linguistic insight. Building upon Weisberg's (2007) notion of a model construal, it is then argued that recent work in computational linguistics to better understand the inner workings of large language models can be used to develop a model construal for large language models as models of a language.

Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. BAIT, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, BAIT's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting BAIT in their evaluation. This paper introduces two methods to enhance BAIT's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of BAIT on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at https://github.com/dhuseljic/dal-toolbox.

Structured pruning for large language models (LLMs) has garnered significant academic interest due to its ability to efficiently compress and accelerate LLMs by eliminating redundant weight groups at a coarse-grained granularity. Current structured pruning methods for LLMs typically depend on a singular granularity for assessing weight importance, resulting in notable performance degradation in downstream tasks. Intriguingly, our empirical investigations reveal that utilizing unstructured pruning, which achieves better performance retention by pruning weights at a finer granularity, \emph{i.e.}, individual weights, yields significantly varied sparse LLM structures when juxtaposed to structured pruning. This suggests that evaluating both holistic and individual assessment for weight importance is essential for LLM pruning. Building on this insight, we introduce the Hybrid-grained Weight Importance Assessment (HyWIA), a novel method that merges fine-grained and coarse-grained evaluations of weight importance for the pruning of LLMs. Leveraging an attention mechanism, HyWIA adaptively determines the optimal blend of granularity in weight importance assessments in an end-to-end pruning manner. Extensive experiments on LLaMA-V1/V2, Vicuna, Baichuan, and Bloom across various benchmarks demonstrate the effectiveness of HyWIA in pruning LLMs. For example, HyWIA surpasses the cutting-edge LLM-Pruner by an average margin of 2.82% in accuracy across seven downstream tasks when pruning LLaMA-7B by 50%. Code:https://github.com/azuryl/LLM-HWIA

The paper extends an existing Intelligent Tutoring System (ITS) that supports students' learning via AI-driven personalized hints and can generate explanations to justify why/how the hints were generated. In this work, we investigate personalizing these hint explanations to students with low levels of two traits, Need for Cognition and Conscientiousness in order to enhance their engagement with the explanations, based on prior findings that these students generally do not ask for the explanations although they would benefit from them. We evaluate the effectiveness of the personalized hint explanations with a formal user study. Our results show that the personalization increases our target users' interaction with the hint explanations, their understanding of the hints, and their learning. Hence, this work contributes to exiting initial evidence on the value of Personalized Explainable AI (PXAI) in education.

Multimodal federated learning (MFL) aims to enrich model training in FL settings where clients are collecting measurements across multiple modalities. However, key challenges to MFL remain unaddressed, particularly in heterogeneous network settings where: (i) the set of modalities collected by each client is diverse, and (ii) communication limitations prevent clients from uploading all their locally trained modality encoders to the server. In this paper, we propose Multimodal Federated learning with joint Modality and Client selection (MFedMC), a communication-efficient MFL framework that tackles these challenges through a decoupled architecture and selective uploading. Unlike traditional holistic fusion approaches, MFedMC separates modality encoders and fusion modules: modality encoders are aggregated at the server for generalization across diverse client distributions, while fusion modules remain local to each client for personalized adaptation to individual modality configurations and data characteristics. Building on this decoupled design, our joint selection algorithm incorporates two main components: (a) A modality selection methodology for each client, which weighs (i) the impact of the modality, gauged by Shapley value analysis, (ii) the modality encoder size as a gauge of communication overhead, and (iii) the frequency of modality encoder updates, denoted recency, to enhance generalizability. (b) A client selection strategy for the server based on the local loss of modality encoders at each client. Experiments on five real-world datasets demonstrate that MFedMC achieves comparable accuracy to several baselines while reducing communication overhead by over 20$\times$. A demo video and our code are available at https://liangqiy.com/mfedmc/.

Mixture-of-experts (MoE) models provide a flexible statistical framework for modeling heterogeneity and nonlinear relationships. In many modern applications, however, datasets are naturally distributed across multiple machines due to storage, computational, or governance constraints. We consider a distributed model aggregation setting in which local MoE models are trained independently on decentralized datasets and subsequently combined into a global estimator. Aggregating MoE models is challenging because standard averaging produces models that do not preserve the MoE structure, and therefore do not yield estimates of the global model parameters. To address this issue, we propose a principled aggregation framework based on optimal transport that constructs a reduced global MoE estimator by minimizing a transportation divergence between the collection of local estimators and the aggregated model. An efficient majorization--minimization (MM) algorithm is derived to solve the resulting optimization problem. The method requires only a single communication step from local machines to a central server, making it a frugal distributed learning approach particularly attractive for large-scale settings where communication costs are a major bottleneck. We further establish statistical guarantees for the aggregated estimator, including consistency under standard assumptions on the local estimators. Experiments on synthetic and real datasets demonstrate that the approach achieves performance comparable to centralized training while significantly reducing computation time. The source codes are publicly available on Github.

Travel behavior prediction is a core problem in transportation demand management and is traditionally addressed using numerical models calibrated on observed data. With recent advances in large language models (LLMs), new opportunities have emerged to model human decision-making through natural language reasoning. This study explores the use of LLMs for travel behavior prediction through two complementary frameworks. The first framework employs a zero-shot prompting strategy, where the prediction task, traveler attributes, and relevant domain knowledge are described in text, enabling the LLM to directly generate predictions without task-specific training data. The second framework uses LLM-generated text embeddings as high-level representations of travel scenarios, which are then combined with conventional supervised learning models to support prediction in small-sample settings. Empirical results show that both approaches achieve performance comparable to, and in some cases competitive with, classical models such as multinomial logit, random forest, and neural networks. These findings suggest that LLMs offer a flexible and data-efficient alternative for travel behavior prediction.

Laplace's method approximates a target density with a Gaussian distribution at its mode. It is computationally efficient and asymptotically exact for Bayesian inference due to the Bernstein-von Mises theorem, but for complex targets and finite-data posteriors it is often too crude an approximation. A recent generalization of the Laplace Approximation transforms the Gaussian approximation according to a chosen Riemannian geometry providing a richer approximation family, while still retaining computational efficiency. However, as shown here, its properties depend heavily on the chosen metric, indeed the metric adopted in previous work results in approximations that are overly narrow as well as being biased even at the limit of infinite data. We correct this shortcoming by developing the approximation family further, deriving two alternative variants that are exact at the limit of infinite data, extending the theoretical analysis of the method, and demonstrating practical improvements in a range of experiments.

The joint optimization of physical parameters and controllers in robotic systems is challenging. This is due to the difficulties of predicting the effect that changes in physical parameters have on final performances. At the same time, physical and morphological modifications can improve robot capabilities, perhaps completely unlocking new skills and tasks. We present a novel approach to co-optimize the physical layout and the control of a cooperative aerial transportation system. The goal is to achieve the most precise and robust flight when carrying a payload. We assume the agents are connected to the payload through rigid attachments, essentially transforming the whole system into a larger flying object with ``thrust modules" at the attachment locations of the quadcopters. We investigate the optimal arrangement of the thrust modules around the payload, so that the resulting system achieves the best disturbance rejection capabilities. We propose a novel metric of robustness inspired by H2 control, and propose an algorithm to optimize the layout of the vehicles around the object and their controller altogether. We experimentally validate the effectiveness of our approach using fleets of three and four quadcopters and payloads of diverse shapes.

Passive hyperspectral longwave infrared measurements are remarkably informative about the surroundings. Remote object material and temperature determine the spectrum of thermal radiance, and range, air temperature, and gas concentrations determine how this spectrum is modified by propagation to the sensor. We introduce a passive range imaging method based on computationally separating these phenomena. Previous methods assume hot and highly emitting objects; ranging is more challenging when objects' temperatures do not deviate greatly from air temperature. Our method jointly estimates range and intrinsic object properties, with explicit consideration of air emission, though reflected light is assumed negligible. Inversion being underdetermined is mitigated by using a parametric model of atmospheric absorption and regularizing for smooth emissivity estimates. To assess where our estimate is likely accurate, we introduce a technique to detect which scene pixels are significantly influenced by reflected downwelling. Monte Carlo simulations demonstrate the importance of regularization, temperature differentials, and availability of many spectral bands. We apply our method to longwave infrared (8--13 $μ$m) hyperspectral image data acquired from natural scenes with no active illumination. Range features from 15m to 150m are recovered, with good qualitative match to lidar data for pixels classified as having negligible reflected downwelling.

Since DARPA started Grand Challenges in 2004 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. This paper gives an overview about technical aspects of autonomous driving technologies and open problems. We investigate the major fields of self-driving systems, such as perception, mapping and localization, prediction, planning and control, simulation, V2X and safety etc. Especially we elaborate on all these issues in a framework of data closed loop, a popular platform to solve the long tailed autonomous driving problems.

Both Minsky's "society of mind" and Schmidhuber's "learning to think" inspire diverse societies of large multimodal neural networks (NNs) that solve problems by interviewing each other in a "mindstorm." Recent implementations of NN-based societies of minds consist of large language models (LLMs) and other NN-based experts communicating through a natural language interface. In doing so, they overcome the limitations of single LLMs, improving multimodal zero-shot reasoning. In these natural language-based societies of mind (NLSOMs), new agents -- all communicating through the same universal symbolic language -- are easily added in a modular fashion. To demonstrate the power of NLSOMs, we assemble and experiment with several of them (having up to 129 members), leveraging mindstorms in them to solve some practical AI tasks: visual question answering, image captioning, text-to-image synthesis, 3D generation, egocentric retrieval, embodied AI, and general language-based task solving. We view this as a starting point towards much larger NLSOMs with billions of agents-some of which may be humans. And with this emergence of great societies of heterogeneous minds, many new research questions have suddenly become paramount to the future of artificial intelligence. What should be the social structure of an NLSOM? What would be the (dis)advantages of having a monarchical rather than a democratic structure? How can principles of NN economies be used to maximize the total reward of a reinforcement learning NLSOM? In this work, we identify, discuss, and try to answer some of these questions.

Low-rank matrix completion consists of computing a matrix of minimal complexity that recovers a given set of observations as accurately as possible. Unfortunately, existing methods for matrix completion are heuristics that, while highly scalable and often identifying high-quality solutions, do not provide an instance-wise certificate of optimality. We reexamine matrix completion with an optimality-oriented eye. We reformulate low-rank matrix completion problems as convex problems over the non-convex set of projection matrices and implement a disjunctive branch-and-bound scheme that solves them to certifiable optimality. Further, we derive a novel and often near-exact class of convex relaxations by decomposing a low-rank matrix as a sum of rank-one matrices and incentivizing that two-by-two minors in each rank-one matrix have determinant zero. In numerical experiments, our new convex relaxations decrease the optimality gap by two orders of magnitude compared to existing attempts, and our disjunctive branch-and-bound scheme solves $n \times m$ rank-$k$ matrix completion problems to certifiable optimality or near optimality in hours for $\max \{m, n\} \leq 2500$ and $k \leq 5$. Moreover, this reduction in the training error translates into an average $2\%$--$50\%$ reduction in the test set error compared with alternating minimization-based methods.

We provide an improved assessment of Google Brain's deep reinforcement learning approach to macro placement and its updated Circuit Training (CT) implementation in GitHub. A stronger simulated annealing (SA) baseline leverages the "go-with-the-winners" metaheuristic and a multi-threading implementation. We develop and release new public benchmarks in sub-10nm technology: LEF/DEF for Google's 7nm TSMC Ariane protobuf and scaled variants, as well as testcases implemented in the open-source ASAP7 7nm research enablement. We evaluate from-scratch training and fine-tuning results for the latest "AlphaChip" release of Circuit Training, alongside multiple alternative macro placers. We also study the recently-published pre-training guidance in. A commercial place-and-route tool is used to provide "true reward" post-route power, performance and area metrics. All data, evaluation flows and related scripts are publicly available in the MacroPlacement GitHub repository. Our study affords insights into reproducibility and reporting in the research literature, and points out still-missing confirmations (e.g., of CT's scalability and pre-training methodology) that remain open questions for the research community.

The concern about hidden discrimination in machine learning models is growing, as their widespread real-world applications increasingly impact human lives. Various techniques, including commonly used group fairness measures and several fairness-aware ensemble-based methods, have been developed to enhance fairness. However, existing fairness measures typically focus on only one aspect -- either group or individual fairness, and the compatibility difficulty among these measures indicates a possibility of remaining biases even when one of them is satisfied. Moreover, existing mechanisms to boost fairness usually present empirical results to show validity, yet few of them discuss whether fairness can be boosted with certain theoretical guarantees. To address these issues, we propose a fairness quality measure named `discriminative risk' by only perturbing protected attributes in instances, to express both individual and group fairness aspects. Furthermore, we investigate its properties and establish the first- and second-order oracle bounds and their relaxations, which show that fairness is possibly improved via ensemble combination with margin-dependent bounds. The analysis is suitable for both binary and multi-class classification. A few ensemble pruning methods are also proposed to utilise our proposed measure and obtain both accurate and fair sub-ensembles; comprehensive experiments are conducted to evaluate the effectiveness of the proposed fairness measure and pruning methods.

Deep active learning (AL) selects batches of instances for annotation to avoid retraining deep neural networks (DNNs) after each new label. Employing a naive top-$b$ selection can result in a batch of redundant (similar) instances. To address this, various AL strategies employ clustering techniques that ensure diversity within a batch. We approach this issue by substituting the costly retraining with an efficient Bayesian update. Our proposed update represents a second-order optimization step using the Gaussian posterior from a last-layer Laplace approximation. Thereby, we achieve low computational complexity by computing the inverse Hessian in closed form. We demonstrate that in typical AL settings, our update closely approximates retraining while being considerably faster. Leveraging our update, we introduce a new framework for batch selection through sequential construction, updating the DNN after each label acquisition. Furthermore, we incorporate our update into a look-ahead selection strategy as a feasible upper baseline approximating optimal batch selection. Our results highlight the potential of efficient updates to advance deep AL research.

Multiple Object Tracking (MOT) is a core capability in modern computer vision, essential to autonomous driving, surveillance, sports analytics, robotics, and biomedical imaging. Persistent identity assignment across frames remains challenging in real scenes because of occlusion, dense crowds, appearance ambiguity, scale variation, camera motion, and identity switching. In this survey we synthesize recent progress by organizing methods around the problems they target and the paradigms they adopt. We cover the historical progression from tracking-by-detection to hybrid and end-to-end designs, and we summarize major architectural directions including transformer-based trackers, generative/diffusion formulations, state-space predictors, Siamese and graph-based models, and the growing impact of foundation models for detection and representation. We review benchmark trends that motivate method design, documenting the shift from saturated pedestrian benchmarks to challenge-driven and domain-specific datasets and we analyze evaluation practice by comparing classic and newer motion- and safety-centric metrics. Finally, we connect algorithmic trends to practical deployment constraints and outline emerging directions, foundation-model integration, open-vocabulary and multimodal tracking, unified evaluation, and domain-adaptive methods, that we believe will shape MOT research and real-world adoption.

Pseudo-relevance feedback (PRF) methods built on large language models (LLMs) can be organized along two key design dimensions: the feedback source, which is where the feedback text is derived from and the feedback model, which is how the given feedback text is used to refine the query representation. However, the independent role that each dimension plays is unclear, as both are often entangled in empirical evaluations. In this paper, we address this gap by systematically studying how the choice of feedback source and feedback model impact PRF effectiveness through controlled experimentation. Across 13 low-resource BEIR tasks with five LLM PRF methods, our results show: (1) the choice of feedback model can play a critical role in PRF effectiveness; (2) feedback derived solely from LLM-generated text provides the most cost-effective solution; and (3) feedback derived from the corpus is most beneficial when utilizing candidate documents from a strong first-stage retriever. Together, our findings provide a better understanding of which elements in the PRF design space are most important.

The rapid evolution and inherent complexity of modern software requirements demand highly flexible and responsive development methodologies. While Agile frameworks have become the industry standard for prioritizing iteration, collaboration, and adaptability, software development teams continue to face persistent challenges in managing constantly evolving requirements and maintaining product quality under tight deadlines. This article explores the intersection of Artificial Intelligence (AI) and Software Engineering (SE), to analyze how AI serves as a powerful catalyst for enhancing agility and fostering innovation. The research combines a comprehensive review of existing literature with an empirical study, utilizing a survey directed at Software Engineering professionals to assess the perception, adoption, and impact of AI-driven tools. Key findings reveal that the integration of AI (specifically through Machine Learning (ML) and Natural Language Processing (NLP) )facilitates the automation of tedious tasks, from requirement management to code generation and testing . This paper demonstrates that AI not only optimizes current Agile practices but also introduces new capabilities essential for sustaining quality, speed, and innovation in the future landscape of software development.

Deep learning models are being used for the analysis of parametric statistical models based on simulation-only frameworks. Bayesian models using normalizing flows simulate data from a prior distribution and are composed of two deep neural networks: a summary network that learns a sufficient statistic for the parameter and a normalizing flow that conditional on the summary network can approximate the posterior distribution. Here, we explore frequentist models that are based on a single summary network. During training, input of the network is a simulated data set based on a parameter and the loss function minimizes the mean-square error between learned summary and parameter. The network thereby solves the inverse problem of parameter estimation. We propose a branched network structure that contains collapsing layers that reduce a data set to summary statistics that are further mapped through fully connected layers to approximate the parameter estimate. We motivate our choice of network structure by theoretical considerations. In simulations we demonstrate three desirable properties of parameter estimates: finite sample exactness, robustness to data contamination, and algorithm approximation. These properties are achieved offering the the network varying sample size, contaminated data, and data needing algorithmic reconstruction during the training phase. In our simulations an EM-algorithm for genetic data is automatically approximated by the network. Simulation only approaches seem to offer practical advantages in complex modeling tasks where the simpler data simulation part is left to the researcher and the more complex problem of solving the inverse problem is left to the neural network. Challenging future work includes offering pre-trained models that can be used in a wide variety of applications.

Simulation-based testing has become a standard approach to validating autonomous driving agents prior to real-world deployment. A high-quality validation campaign will exercise an agent in diverse contexts comprised of varying static environments, e.g., lanes, intersections, signage, and dynamic elements, e.g., vehicles and pedestrians. To achieve this, existing test generation techniques rely on template-based, manually constructed, or random scenario generation. When applied to validate formally specified safety requirements, such methods either require significant human effort or run the risk of missing important behavior related to the requirement. To address this gap, we present STADA, a Specification-based Test generation framework for Autonomous Driving Agents that systematically generates the space of scenarios defined by a formal specification expressed in temporal logic (LTLf). Given a specification, STADA constructs all distinct initial scenes, a diverse space of continuations of those scenes, and simulations that reflect the behaviors of the specification. Evaluation of STADA on a variety of LTLf specifications formalized in SCENEFLOW using three complementary coverage criteria demonstrates that STADA yields more than 2x higher coverage than the best baseline on the finest criteria and a 75% increase for the coarsest criteria. Moreover, it matches the coverage of the best baseline with 6 times fewer simulations. While set in the context of autonomous driving, the approach is applicable to other domains with rich simulation environments.

This paper addresses the problem of dual-technology scheduling in hybrid Internet-of-Things (IoT) networks that integrate Optical Wireless Communication (OWC) with Radio Frequency (RF). We first present an optimization formulation that jointly maximizes throughput and minimizes delivery-based Age of Information (AoI) between access points and IoT nodes under energy and link availability constraints. However, solving such NP-hard problems at scale is computationally intractable and typically assumes full channel observability, which is impractical in real deployments. To address this challenge, we propose the Dual-Graph Embedding with Transformer (DGET) framework, a supervised multi-task learning architecture that combines a two-stage Graph Neural Network (GNN) with a Transformer encoder. The first stage employs a transductive GNN to encode the known graph topology together with initial node and link states, such as energy levels, available links, and queued transmissions. The second stage introduces an inductive GNN for temporal refinement, enabling the model to generalize these embeddings to evolving network states while capturing variations in energy and queue dynamics over time through a consistency loss. The resulting embeddings are then processed by a Transformer-based classifier that models cross-link dependencies using multi-head self-attention. Simulation results show that hybrid RF-OWC networks outperform standalone RF systems by supporting higher traffic loads and reducing AoI by up to 20% while maintaining comparable energy consumption. Compared with optimization-based methods, the proposed DGET framework achieves near-optimal scheduling with over 90% classification accuracy, lower computational complexity, and improved robustness under partial channel observability.