For a responsible and safe deployment of diffusion models in various domains, regulating the generated outputs from these models is desirable because such models could generate undesired, violent, and obscene outputs. To tackle this problem, recent works use machine unlearning methodology to forget training data points containing these undesired features from pre-trained generative models. However, these methods proved to be ineffective in data-constrained settings where the whole training dataset is inaccessible. Thus, the principal objective of this work is to propose a machine unlearning methodology that can prevent the generation of outputs containing undesired features from a pre-trained diffusion model in such a data-constrained setting. Our proposed method, termed as Variational Diffusion Unlearning (VDU), is a computationally efficient method that only requires access to a subset of training data containing undesired features. Our approach is inspired by the variational inference framework with the objective of minimizing a loss function consisting of two terms: plasticity inducer and stability regularizer. Plasticity inducer reduces the log-likelihood of the undesired training data points, while the stability regularizer, essential for preventing loss of image generation quality, regularizes the model in parameter space. We validate the effectiveness of our method through comprehensive experiments for both class unlearning and feature unlearning. For class unlearning, we unlearn some user-identified classes from MNIST, CIFAR-10, and tinyImageNet datasets from a pre-trained unconditional denoising diffusion probabilistic model (DDPM). Similarly, for feature unlearning, we unlearn the generation of certain high-level features from a pre-trained Stable Diffusion model

Ensuring native-like quality of large language model (LLM) responses across many languages is challenging. Our evaluation reveals that zero-shot LLM judges benefit significantly from pairwise evaluation and our structured annotation rubrics, yet they still underperform human annotators on our dataset. We demonstrate substantial improvements through fine-tuning with reinforcement learning, reward shaping, and multi-task learning approaches. Additionally, we show that RL-trained judges can serve as generative reward models to enhance LLMs' multilingual proficiency, though discrepancies with human judgment remain. Our findings suggest promising directions for scalable multilingual evaluation and preference alignment. We release our dataset and evaluation framework to support further research in multilingual LLM evaluation.Dataset https://huggingface.co/datasets/facebook/menlo In order for LLMs to be most useful across the globe, they need to be able to provide high-quality responses in many languages. Responses should be relevant (Zhuang et al., 2024), factually accurate (Jacovi et al., 2025), and natural (Marchisio et al., 2024; Guo et al., 2025), among other considerations. Ultimately, for interaction in any language to be seamless, responses need to be indistinguishable from those of a native speaker (Novikova et al., 2016; Liu et al., 2021). Language proficiency in humans has traditionally been evaluated via standardized tests (Jamieson et al., 2000). While such tests have been applied to evaluating LLMs (Anil et al., 2023; Mayor-Rocher et al., 2024; Lothritz & Cabot, 2025), they are difficult to scale and do not readily correspond to real-world conversations.

The empirically established null subject (NS) stage, lasting until about 4 years of age, involves frequent omission of subjects by children. Orfitelli and Hyams (2012) observe that young English speakers often confuse imperative NS utterances with declarative ones due to performance influences, promoting a temporary null subject grammar. We propose a new computational parameter to measure this misinterpretation and incorporate it into a simulated model of obligatory subject grammar learning. Using a modified version of the Variational Learner (Yang, 2012) which works for superset-subset languages, our simulations support Orfitelli and Hyams' hypothesis. More generally, this study outlines a framework for integrating computational models in the study of grammatical acquisition alongside other key developmental factors.

Time-series anomaly detection (TSAD) increasingly demands explanations that articulate not only if an anomaly occurred, but also what pattern it exhibits and why it is anomalous. Leveraging the impressive explanatory capabilities of Large Language Models (LLMs), recent works have attempted to treat time series as text for explainable TSAD. However, this approach faces a fundamental challenge: LLMs operate on discrete tokens and struggle to directly process long, continuous signals. Consequently, naive time-to-text serialization suffers from a lack of contextual grounding and representation alignment between the two modalities. To address this gap, we introduce AXIS, a framework that conditions a frozen LLM for nuanced time-series understanding. Instead of direct serialization, AXIS enriches the LLM's input with three complementary hints derived from the series: (i) a symbolic numeric hint for numerical grounding, (ii) a context-integrated, step-aligned hint distilled from a pretrained time-series encoder to capture fine-grained dynamics, and (iii) a task-prior hint that encodes global anomaly characteristics. Furthermore, to facilitate robust evaluation of explainability, we introduce a new benchmark featuring multi-format questions and rationales that supervise contextual grounding and pattern-level semantics. Extensive experiments, including both LLM-based and human evaluations, demonstrate that AXIS yields explanations of significantly higher quality and achieves competitive detection accuracy compared to general-purpose LLMs, specialized time-series LLMs, and time-series Vision Language Models.

Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates \textbf{System 1} (fast, intuitive thinking) and \textbf{System 2} (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent (System 1) to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for \textit{planning}, \textit{hypothesis generation}, \textit{retrieval}, \textit{information integration}, and \textit{decision-making}. This multi-agent design faithfully mimics human cognitive processes and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.

Clinical dataset labels are rarely certain as annotators disagree and confidence is not uniform across cases. Typical aggregation procedures, such as majority voting, obscure this variability. In simple experiments on medical imaging benchmarks, accounting for the confidence in binary labels significantly impacts model rankings. We therefore argue that machine-learning evaluations should explicitly account for annotation uncertainty using probabilistic metrics that directly operate on distributions. These metrics can be applied independently of the annotations' generating process, whether modeled by simple counting, subjective confidence ratings, or probabilistic response models. They are also computationally lightweight, as closed-form expressions have linear-time implementations once examples are sorted by model score. We thus urge the community to release raw annotations for datasets and to adopt uncertainty-aware evaluation so that performance estimates may better reflect clinical data.

Federated continual learning (FCL) enables distributed client devices to learn from streaming data across diverse and evolving tasks. A major challenge to continual learning, catastrophic forgetting, is exacerbated in decentralized settings by the data heterogeneity, constrained communication and privacy concerns. We propose Federated gradient Projection-based Continual Learning with Task Identity Prediction (FedProTIP), a novel FCL framework that mitigates forgetting by projecting client updates onto the orthogonal complement of the subspace spanned by previously learned representations of the global model. This projection reduces interference with earlier tasks and preserves performance across the task sequence. To further address the challenge of task-agnostic inference, we incorporate a lightweight mechanism that leverages core bases from prior tasks to predict task identity and dynamically adjust the global model's outputs. Extensive experiments across standard FCL benchmarks demonstrate that FedProTIP significantly outperforms state-of-the-art methods in average accuracy, particularly in settings where task identities are a priori unknown.

Large Language Models (LLMs) exhibit strong reasoning capabilities in complex tasks. However, they still struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA). We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures. Existing methods usually employ resource-intensive, non-scalable workflows reasoning on vanilla KGs, but overlook this gap. To address this challenge, we propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries. EoG enables efficient evidence extraction from KGs for precise and robust reasoning, while ensuring low computational costs, scalability, and adaptability across different methods. Furthermore, we propose three graph quality evaluation metrics to analyze query-graph alignment in KGQA task, supported by theoretical validation of our optimization objectives. Extensive experiments on two KGQA benchmark datasets indicate that EoG can effectively generate high-quality KGs and achieve the state-of-the-art performance. Our code and data are available at https://github.com/zjukg/Enrich-on-Graph.

Abstract-- This paper proposes an uncertainty-aware marine pollution source tracking framework for unmanned surface vehicles (USVs). By integrating high-fidelity marine pollution dispersion simulation with informative path planning techniques, we demonstrate effective identification of pollution sources in marine environments. The proposed approach is implemented based on Robot Operating System (ROS), processing real-time sensor data to update probabilistic source location estimates. Experiments conducted in simulated environments with varying source locations, wave conditions, and starting positions demonstrate the framework's ability to localise pollution sources with high accuracy. Results show that the proposed approach achieves reliable source localisation efficiently and outperforms the existing baseline. This work contributes to the development of full autonomous environmental monitoring capabilities essential for rapid response to marine pollution incidents. Pollution discharged into the marine environment causes severe consequences to ecosystems [1], [2] and human health [3].

Today's cyber defenders are overwhelmed by a deluge of security alerts, threat intelligence signals, and shifting business context, creating an urgent need for AI systems to enhance operational security work. While Large Language Models (LLMs) have the potential to automate and scale Security Operations Center (SOC) operations, existing evaluations do not fully assess the scenarios most relevant to real-world defenders. This lack of informed evaluation impacts both AI developers and those applying LLMs to SOC automation. Without clear insight into LLM performance in real-world security scenarios, developers lack a north star for development, and users cannot reliably select the most effective models. Meanwhile, malicious actors are using AI to scale cyber attacks, highlighting the need for open source benchmarks to drive adoption and community-driven improvement among defenders and model developers. To address this, we introduce CyberSOCEval, a new suite of open source benchmarks within CyberSecEval 4. CyberSOCEval includes benchmarks tailored to evaluate LLMs in two tasks: Malware Analysis and Threat Intelligence Reasoning--core defensive domains with inadequate coverage in current benchmarks. Our evaluations show that larger, more modern LLMs tend to perform better, confirming the training scaling laws paradigm. We also find that reasoning models leveraging test time scaling do not achieve the same boost as in coding and math, suggesting these models have not been trained to reason about cybersecurity analysis, and pointing to a key opportunity for improvement. Finally, current LLMs are far from saturating our evaluations, showing that CyberSOCEval presents a significant challenge for AI developers to improve cyber defense capabilities.