The rapid progress of Large Language Models (LLMs) has transformed natural language processing and broadened its impact across research and society. Yet, systematic evaluation of these models, especially for languages beyond English, remains limited. "Challenging the Abilities of LAnguage Models in ITAlian" (CALAMITA) is a large-scale collaborative benchmarking initiative for Italian, coordinated under the Italian Association for Computational Linguistics. Unlike existing efforts that focus on leaderboards, CALAMITA foregrounds methodology: it federates more than 80 contributors from academia, industry, and the public sector to design, document, and evaluate a diverse collection of tasks, covering linguistic competence, commonsense reasoning, factual consistency, fairness, summarization, translation, and code generation. Through this process, we not only assembled a benchmark of over 20 tasks and almost 100 subtasks, but also established a centralized evaluation pipeline that supports heterogeneous datasets and metrics. We report results for four open-weight LLMs, highlighting systematic strengths and weaknesses across abilities, as well as challenges in task-specific evaluation. Beyond quantitative results, CALAMITA exposes methodological lessons: the necessity of fine-grained, task-representative metrics, the importance of harmonized pipelines, and the benefits and limitations of broad community engagement. CALAMITA is conceived as a rolling benchmark, enabling continuous integration of new tasks and models. This makes it both a resource -- the most comprehensive and diverse benchmark for Italian to date -- and a framework for sustainable, community-driven evaluation. We argue that this combination offers a blueprint for other languages and communities seeking inclusive and rigorous LLM evaluation practices.

This article serves as the regression analysis lecture notes in the Intelligent Computing course cluster (including the courses of Artificial Intelligence, Data Mining, Machine Learning, and Pattern Recognition). It aims to provide students -- who are assumed to possess only basic university-level mathematics (i.e., with prerequisite courses in calculus, linear algebra, and probability theory) -- with a comprehensive and self-contained understanding of regression analysis without requiring any additional references. The lecture notes systematically introduce the fundamental concepts, modeling components, and theoretical foundations of regression analysis, covering linear regression, logistic regression, multinomial logistic regression, polynomial regression, basis-function models, kernel-based methods, and neural-network-based nonlinear regression. Core methodological topics include loss-function design, parameter-estimation principles, ordinary least squares, gradient-based optimization algorithms and their variants, as well as regularization techniques such as Ridge and LASSO regression. Through detailed mathematical derivations, illustrative examples, and intuitive visual explanations, the materials help students understand not only how regression models are constructed and optimized, but also how they reveal the underlying relationships between features and response variables. By bridging classical statistical modeling and modern machine-learning practice, these lecture notes aim to equip students with a solid conceptual and technical foundation for further study in advanced artificial intelligence models.

In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of Decoupled Knowledge Distillation (DKD), which re-emphasizes the importance of logit knowledge through advanced decoupling and weighting strategies. While DKD marks a significant advancement, its underlying mechanisms merit deeper exploration. As a response, we rethink DKD from a predictive distribution perspective. First, we introduce an enhanced version, the Generalized Decoupled Knowledge Distillation (GDKD) loss, which offers a more versatile method for decoupling logits. Then we pay particular attention to the teacher model's predictive distribution and its impact on the gradients of GDKD loss, uncovering two critical insights often overlooked: (1) the partitioning by the top logit considerably improves the interrelationship of non-top logits, and (2) amplifying the focus on the distillation loss of non-top logits enhances the knowledge extraction among them. Utilizing these insights, we further propose a streamlined GDKD algorithm with an efficient partition strategy to handle the multimodality of teacher models' predictive distribution. Our comprehensive experiments conducted on a variety of benchmarks, including CIFAR-100, ImageNet, Tiny-ImageNet, CUB-200-2011, and Cityscapes, demonstrate GDKD's superior performance over both the original DKD and other leading knowledge distillation methods. The code is available at https://github.com/ZaberKo/GDKD.

Open-world learning (OWL) requires models that can adapt to evolving environments while reliably detecting out-of-distribution (OOD) inputs. Existing approaches, such as SCONE, achieve robustness to covariate and semantic shifts but assume static environments, leading to degraded performance in dynamic domains. In this paper, we propose Temp-SCONE, a temporally consistent extension of SCONE designed to handle temporal shifts in dynamic environments. Temp-SCONE introduces a confidence-driven regularization loss based on Average Thresholded Confidence (ATC), penalizing instability in predictions across time steps while preserving SCONE's energy-margin separation. Experiments on dynamic datasets demonstrate that Temp-SCONE significantly improves robustness under temporal drift, yielding higher corrupted-data accuracy and more reliable OOD detection compared to SCONE. On distinct datasets without temporal continuity, Temp-SCONE maintains comparable performance, highlighting the importance and limitations of temporal regularization. Our theoretical insights on temporal stability and generalization error further establish Temp-SCONE as a step toward reliable OWL in evolving dynamic environments.

Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which seeks to accurately and efficiently modify a model's internal (parametric) knowledge without retraining it from scratch. However, existing methods suffer from two limitations. First, they depend on structured triplets that are misaligned with the free-text nature of LLM pretraining and fail to capture the nuanced relationships among facts. Second, they typically support one-time knowledge updates, with relatively limited research on the problem of sequential or lifelong editing. To address these gaps, we propose a new task, Lifelong Free-text Knowledge Editing (LF-Edit), which enables models to incorporate updates expressed in natural language and supports continual editing over time. Despite its promise, LF-Edit faces the dual challenge of integrating new knowledge while mitigating the forgetting of prior information. To foster research on this new task, we construct a large-scale benchmark, Multi-Rank Lifelong Free-text Editing Benchmark (MRLF-Bench), containing 16,835 free-text edit requests. We further design a cognitively inspired multi-rank evaluation framework encompassing four levels: memorization, understanding, constrained comprehension, and reasoning. To tackle the challenges inherent in LF-Edit, we introduce a novel approach named EvoEdit that enhances knowledge injection through Latent Perturbation Augmentation and preserves prior information via Knowledge-driven Parameter Fusion. Experimental results demonstrate that EvoEdit substantially outperforms existing knowledge editing methods on the proposed LF-Edit task.

Knowledge distillation is an effective and hardware-friendly method, which plays a key role in lightweighting remote sensing object detection. However, existing distillation methods often encounter the issue of mixed features in remote sensing images (RSIs), and neglect the discrepancies caused by subtle feature variations, leading to entangled knowledge confusion. To address these challenges, we propose an architecture-agnostic distillation method named Dual-Stream Spectral Decoupling Distillation (DS2D2) for universal remote sensing object detection tasks. Specifically, DS2D2 integrates explicit and implicit distillation grounded in spectral decomposition. Firstly, the first-order wavelet transform is applied for spectral decomposition to preserve the critical spatial characteristics of RSIs. Leveraging this spatial preservation, a Density-Independent Scale Weight (DISW) is designed to address the challenges of dense and small object detection common in RSIs. Secondly, we show implicit knowledge hidden in subtle student-teacher feature discrepancies, which significantly influence predictions when activated by detection heads. This implicit knowledge is extracted via full-frequency and high-frequency amplifiers, which map feature differences to prediction deviations. Extensive experiments on DIOR and DOTA datasets validate the effectiveness of the proposed method. Specifically, on DIOR dataset, DS2D2 achieves improvements of 4.2% in AP50 for RetinaNet and 3.8% in AP50 for Faster R-CNN, outperforming existing distillation approaches. The source code will be available at https://github.com/PolarAid/DS2D2.

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through interactions with an environment guided by reward signals. However, when these signals are sparse, delayed, or poorly aligned with the intended task objectives, agents often struggle to learn effectively. Dense reward functions, which provide informative feedback at every step or state transition, offer a potential solution by shaping agent behavior and accelerating learning. Despite their benefits, poorly crafted reward functions can lead to unintended behaviors, reward hacking, or inefficient exploration. This problem is particularly acute in complex or high-dimensional environments where handcrafted rewards are difficult to specify and validate. To address this, recent research has explored a variety of approaches, including inverse reinforcement learning, reward modeling from human preferences, and self-supervised learning of intrinsic rewards. While these methods offer promising directions, they often involve trade-offs between generality, scalability, and alignment with human intent. This proposal explores several approaches to dealing with these unsolved problems and enhancing the effectiveness and reliability of dense reward construction in different RL applications.

Adversarial training is an effective method to improve the machine learning (ML) model robustness. Most existing studies typically consider the Rectified linear unit (ReLU) activation function and centralized training environments. In this paper, we study the ML model robustness using ten different activation functions through adversarial training in centralized environments and explore the ML model robustness in federal learning environments. In the centralized environment, we first propose an advanced adversarial training approach to improving the ML model robustness by incorporating model architecture change, soft labeling, simplified data augmentation, and varying learning rates. Then, we conduct extensive experiments on ten well-known activation functions in addition to ReLU to better understand how they impact the ML model robustness. Furthermore, we extend the proposed adversarial training approach to the federal learning environment, where both independent and identically distributed (IID) and non-IID data settings are considered. Our proposed centralized adversarial training approach achieves a natural and robust accuracy of 77.08% and 67.96%, respectively on CIFAR-10 against the fast gradient sign attacks. Experiments on ten activation functions reveal ReLU usually performs best. In the federated learning environment, however, the robust accuracy decreases significantly, especially on non-IID data. To address the significant performance drop in the non-IID data case, we introduce data sharing and achieve the natural and robust accuracy of 70.09% and 54.79%, respectively, surpassing the CalFAT algorithm, when 40% data sharing is used. That is, a proper percentage of data sharing can significantly improve the ML model robustness, which is useful to some real-world applications.

This paper critiques common patterns in machine ethics for Reinforcement Learning (RL) and argues for a virtue focused alternative. We highlight two recurring limitations in much of the current literature: (i) rule based (deontological) methods that encode duties as constraints or shields often struggle under ambiguity and nonstationarity and do not cultivate lasting habits, and (ii) many reward based approaches, especially single objective RL, implicitly compress diverse moral considerations into a single scalar signal, which can obscure trade offs and invite proxy gaming in practice. We instead treat ethics as policy level dispositions, that is, relatively stable habits that hold up when incentives, partners, or contexts change. This shifts evaluation beyond rule checks or scalar returns toward trait summaries, durability under interventions, and explicit reporting of moral trade offs. Our roadmap combines four components: (1) social learning in multi agent RL to acquire virtue like patterns from imperfect but normatively informed exemplars; (2) multi objective and constrained formulations that preserve value conflicts and incorporate risk aware criteria to guard against harm; (3) affinity based regularization toward updateable virtue priors that support trait like stability under distribution shift while allowing norms to evolve; and (4) operationalizing diverse ethical traditions as practical control signals, making explicit the value and cultural assumptions that shape ethical RL benchmarks.

Human-annotated datasets with explicit difficulty ratings are essential in intelligent educational systems. Although embedding vector spaces are widely used to represent semantic closeness and are promising for analyzing text difficulty, the abundance of embedding methods creates a challenge in selecting the most suitable method. This study proposes the Educational Cone Model, which is a geometric framework based on the assumption that easier texts are less diverse (focusing on fundamental concepts), whereas harder texts are more diverse. This assumption leads to a cone-shaped distribution in the embedding space regardless of the embedding method used. The model frames the evaluation of embeddings as an optimization problem with the aim of detecting structured difficulty-based patterns. By designing specific loss functions, efficient closed-form solutions are derived that avoid costly computation. Empirical tests on real-world datasets validated the model's effectiveness and speed in identifying the embedding spaces that are best aligned with difficulty-annotated educational texts.