Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning processes within these interactions presents a significant challenge due to complex contextual dependencies and a lack of specialized visualization tools, leading to a high cognitive load for researchers. To address this gap, we present VIST A, an web-based Visual Interactive System for Textual Analytics in multi-turn reasoning tasks. VIST A allows users to visualize the influence of context on model decisions and interactively modify conversation histories to conduct "what-if" analyses across different models. Furthermore, the platform can automatically parse a session and generate a reasoning dependency tree, offering a transparent view of the model's step-by-step logical path. By providing a unified and interactive framework, VIST A significantly reduces the complexity of analyzing reasoning chains, thereby facilitating a deeper understanding of the capabilities and limitations of current LLMs. The platform is open-source and supports easy integration of custom benchmarks and local models.

Accurate exploration of protein conformational ensembles is essential for uncovering function but remains hard because molecular-dynamics (MD) simulations suffer from high computational costs and energy-barrier trapping. This paper presents Energy Preference Optimization (EPO), an online refinement algorithm that turns a pretrained protein ensemble generator into an energy-aware sampler without extra MD trajectories. Specifically, EPO leverages stochastic differential equation sampling to explore the conformational landscape and incorporates a novel energy-ranking mechanism based on list-wise preference optimization. Crucially, EPO introduces a practical upper bound to efficiently approximate the intractable probability of long sampling trajectories in continuous-time generative models, making it easily adaptable to existing pretrained generators. On Tetrapeptides, A T - LAS, and Fast-Folding benchmarks, EPO successfully generates diverse and physically realistic ensembles, establishing a new state-of-the-art in nine evaluation metrics. These results demonstrate that energy-only preference signals can efficiently steer generative models toward thermodynamically consistent conformational ensembles, providing an alternative to long MD simulations and widening the applicability of learned potentials in structural biology and drug discovery.

The performance of Machine Learning (ML) models, particularly those operating within the Interpretable Artificial Intelligence (Interpretable AI) framework, is significantly affected by the presence of noise in both training and production data. Denoising has therefore become a critical preprocessing step, typically categorized into instance removal and instance correction techniques. However, existing correction approaches often degrade performance or oversimplify the problem by altering the original data distribution. This leads to unrealistic scenarios and biased models, which is particularly problematic in contexts where interpretable AI models are employed, as their interpretability depends on the fidelity of the underlying data patterns. In this paper, we argue that defining noise independently of the solution may be ineffective, as its nature can vary significantly across tasks and datasets. Using a task-specific high quality solution as a reference can provide a more precise and adaptable noise definition. To this end, we propose DenoGrad, a novel Gradient-based instance Denoiser framework that leverages gradients from an accurate Deep Learning (DL) model trained on the target data -- regardless of the specific task -- to detect and adjust noisy samples. Unlike conventional approaches, DenoGrad dynamically corrects noisy instances, preserving problem's data distribution, and improving AI models robustness. DenoGrad is validated on both tabular and time series datasets under various noise settings against the state-of-the-art. DenoGrad outperforms existing denoising strategies, enhancing the performance of interpretable IA models while standing out as the only high quality approach that preserves the original data distribution.

Retrieval-Augmented Generation (RAG) systems deployed over proprietary knowledge bases face growing threats from reconstruction attacks that aggregate model responses to replicate knowledge bases. Such attacks exploit both intra-class and inter-class paths, progressively extracting fine-grained knowledge within topics and diffusing it across semantically related ones, thereby enabling comprehensive extraction of the original knowledge base. However, existing defenses target only one path, leaving the other unprotected. We conduct a systematic exploration to assess the impact of protecting each path independently and find that joint protection is essential for effective defense. Based on this, we propose RAGFort, a structure-aware dual-module defense combining "contrastive reindexing" for inter-class isolation and "constrained cascade generation" for intra-class protection. Experiments across security, performance, and robustness confirm that RAGFort significantly reduces reconstruction success while preserving answer quality, offering comprehensive defense against knowledge base extraction attacks.

Due to the rapid growth of social media platforms, these tools have become essential for monitoring information during ongoing disaster events. However, extracting valuable insights requires real-time processing of vast amounts of data. A major challenge in existing systems is their exposure to event-related biases, which negatively affects their ability to generalize to emerging events. While recent advancements in debiasing and causal learning offer promising solutions, they remain underexplored in the disaster event domain. In this work, we approach bias mitigation through a causal lens and propose a method to reduce event- and domain-related biases, enhancing generalization to future events. Our approach outperforms multiple baselines by up to +1.9% F1 and significantly improves a PLM-based classifier across three disaster classification tasks.

Humans are remarkably efficient at learning tasks from demonstrations, but today's imitation learning methods for robot manipulation often require hundreds or thousands of demonstrations per task. We investigate two fundamental priors for improving learning efficiency: decomposing manipulation trajectories into sequential alignment and interaction phases, and retrieval-based generalisation. Through 3,450 real-world rollouts, we systematically study this decomposition. We compare different design choices for the alignment and interaction phases, and examine generalisation and scaling trends relative to today's dominant paradigm of behavioural cloning with a single-phase monolithic policy. In the few-demonstrations-per-task regime (<10 demonstrations), decomposition achieves an order of magnitude improvement in data efficiency over single-phase learning, with retrieval consistently outperforming behavioural cloning for both alignment and interaction. Building on these insights, we develop Multi-Task Trajectory Transfer (MT3), an imitation learning method based on decomposition and retrieval. MT3 learns everyday manipulation tasks from as little as a single demonstration each, whilst also generalising to novel object instances. This efficiency enables us to teach a robot 1,000 distinct everyday tasks in under 24 hours of human demonstrator time. Through 2,200 additional real-world rollouts, we reveal MT3's capabilities and limitations across different task families. Videos of our experiments can be found on at https://www.robot-learning.uk/learning-1000-tasks.

I n light of this, we introduce MA TAI, a generalist ML framework for alloy property prediction and inverse design. Unlike task - specific models, MA TAI integrate s domain knowledge from diverse alloy systems and support s multi - objective, constraint - aware optimization across broad compositional spaces . The framework consists of four core components: 1) a holistic alloy database containing over 10,000 experimentally verified compositions, aggregated from open databases, literature, and in - house experiments; 2) foundational property predictor s capable of estimating multiple alloy properties such as density, yield strength (YS), ultimate tensile s trength (UTS), and elongation directly from alloy compositions; 3) a generalist alloy designer that performs constrained optimization over multiple objectives, enabling the discovery of promising alloy candidates without exhaustive searches; and 4) an iterative AI - experiment feedback loop that continuously refines the model through experimental validation of AI - generated candidates . To demonstrate the effectiveness and robustness of MA TAI, we apply the framework to the titanium (Ti) - based alloys, a canonical aerospace alloy system valued for its low density with high strength . Using MA TAI, we identifi ed novel compositions that achieve high strength (>1000 MPa) and moderate elongation (>5%) while retaining a low density (< 4.45 g/cm

-- In this paper, m ilitary use cases or applications and implementation thereof are considered for natural language processing and large language models, which have broken into fame with the invention of the generative pre - trained transformer (GPT) and the extensive foundation model pretraining done by OpenAI for ChatGPT and others . First, we interrogate a GPT - based language model (viz. Microsoft Copilot) to make it reveal its own knowledge about their potential military application s and then critically assess the information . Second, we study how commercial cloud services (viz. Microsoft Azure) could be used readily to build such applications and assess which of the m are feasible. We conclude that t he summarization and generative properties of language models directly facilitate many applications at large and other features may find particular uses . This paper was originally presented at the NATO Science and Technology Organization Symposium (ICMCIS) organized by ...

Post-hoc explainability methods are a subset of Machine Learning (ML) that aim to provide a reason for why a model behaves in a certain way. In this paper, we show a new black-box model-agnostic adversarial attack for post-hoc explainable Artificial Intelligence (XAI), particularly in the image domain. The goal of the attack is to modify the original explanations while being undetected by the human eye and maintain the same predicted class. In contrast to previous methods, we do not require any access to the model or its weights, but only to the model's computed predictions and explanations. Additionally, the attack is accomplished in a single step while significantly changing the provided explanations, as demonstrated by empirical evaluation. The low requirements of our method expose a critical vulnerability in current explainability methods, raising concerns about their reliability in safety-critical applications. We systematically generate attacks based on the explanations generated by post-hoc explainability methods (saliency maps, integrated gradients, and DeepLIFT SHAP) for pretrained ResNet-18 and ViT-B16 on ImageNet. The results show that our attacks could lead to dramatically different explanations without changing the predictive probabilities. We validate the effectiveness of our attack, compute the induced change based on the explanation with mean absolute difference, and verify the closeness of the original image and the corrupted one with the Structural Similarity Index Measure (SSIM).

Urban Network Security Games (UNSGs), which model the strategic allocation of limited security resources on city road networks, are critical for urban safety. However, finding a Nash Equilibrium (NE) in large-scale UNSGs is challenging due to their massive and combinatorial action spaces. One common approach to addressing these games is the Policy-Space Response Oracle (PSRO) framework, which requires computing best responses (BR) at each iteration. However, precisely computing exact BRs is impractical in large-scale games, and employing reinforcement learning to approximate BRs inevitably introduces errors, which limits the overall effectiveness of the PSRO methods. Recent advancements in leveraging non-convex stochastic optimization to approximate an NE offer a promising alternative to the burdensome BR computation. However, utilizing existing stochastic optimization techniques with an unbiased loss function for UNSGs remains challenging because the action spaces are too vast to be effectively represented by neural networks. To address these issues, we introduce Tree-based Stochastic Optimization (TSO), a framework that bridges the gap between the stochastic optimization paradigm for NE-finding and the demands of UNSGs. Specifically, we employ the tree-based action representation that maps the whole action space onto a tree structure, addressing the challenge faced by neural networks in representing actions when the action space cannot be enumerated. We then incorporate this representation into the loss function and theoretically demonstrate its equivalence to the unbiased loss function. To further enhance the quality of the converged solution, we introduce a sample-and-prune mechanism that reduces the risk of being trapped in suboptimal local optima. Extensive experimental results indicate the superiority of TSO over other baseline algorithms in addressing the UNSGs.