Digital Twins (DTs) are gaining prominence in cybersecurity for their ability to replicate complex IT (Information Technology), OT (Operational Technology), and IoT (Internet of Things) infrastructures, allowing for real time monitoring, threat analysis, and system simulation. This study investigates how integrating DTs with penetration testing tools and Large Language Models (LLMs) can enhance cybersecurity education and operational readiness. By simulating realistic cyber environments, this approach offers a practical, interactive framework for exploring vulnerabilities and defensive strategies. At the core of this research is the Red Team Knife (RTK), a custom penetration testing toolkit aligned with the Cyber Kill Chain model. RTK is designed to guide learners through key phases of cyberattacks, including reconnaissance, exploitation, and response within a DT powered ecosystem. The incorporation of Large Language Models (LLMs) further enriches the experience by providing intelligent, real-time feedback, natural language threat explanations, and adaptive learning support during training exercises. This combined DT LLM framework is currently being piloted in academic settings to develop hands on skills in vulnerability assessment, threat detection, and security operations. Initial findings suggest that the integration significantly improves the effectiveness and relevance of cybersecurity training, bridging the gap between theoretical knowledge and real-world application. Ultimately, the research demonstrates how DTs and LLMs together can transform cybersecurity education to meet evolving industry demands.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of LLMs. Existing research has predominantly concentrated on isolated reasoning domains such as mathematical problem-solving, coding tasks, or logical reasoning. However, real world reasoning scenarios inherently demand an integrated application of multiple cognitive skills. Despite this, the interplay among these reasoning skills under reinforcement learning remains poorly understood. To bridge this gap, we present a systematic investigation of multi-domain reasoning within the RLVR framework, explicitly focusing on three primary domains: mathematical reasoning, code generation, and logical puzzle solving. We conduct a comprehensive study comprising four key components: (1) Leveraging the GRPO algorithm and the Qwen-2.5-7B model family, our study thoroughly evaluates the models' in-domain improvements and cross-domain generalization capabilities when trained on single-domain datasets. (2) Additionally, we examine the intricate interactions including mutual enhancements and conflicts that emerge during combined cross-domain training. (3) To further understand the influence of SFT on RL, we also analyze and compare performance differences between base and instruct models under identical RL configurations. (4) Furthermore, we delve into critical RL training details, systematically exploring the impacts of curriculum learning strategies, variations in reward design, and language-specific factors. Through extensive experiments, our results offer significant insights into the dynamics governing domain interactions, revealing key factors influencing both specialized and generalizable reasoning performance. These findings provide valuable guidance for optimizing RL methodologies to foster comprehensive, multi-domain reasoning capabilities in LLMs.

Transformers have become the de facto backbone of modern deep learning, yet their training typically demands an advanced optimizer with adaptive learning rate like AdamW, rather than a momentum SGDW (mSGDW). Previous works show that it is mainly due to a heavy-tailed distribution of the gradients. In this paper, we introduce a Deeply Normalized Transformer (DNT), which is meticulously engineered to overcome this limitation enabling seamless training with vanilla mSGDW while yielding comparable performance to the Transformers trained via AdamW. To be specific, in DNT, we strategically integrate normalization techniques at proper positions in the Transformers to effectively modulate the Jacobian matrices of each layer, balance the influence of weights, activations, and their interactions, and thus enable the distributions of gradients concentrated. We provide both theoretical justifications of the normalization technique used in our DNT and extensive empirical evaluation on two popular Transformer architectures to validate that: a) DNT outperforms its counterparts (\ie, ViT and GPT), and b) DNT can be effectively trained with vanilla mSGDW.

Although recent Large Language Models (LLMs) have shown rapid improvement on reasoning benchmarks in English, the evaluation of such LLMs' multilingual reasoning capability across diverse languages and cultural contexts remains limited. Existing multilingual reasoning benchmarks are typically constructed by translating existing English reasoning benchmarks, biasing these benchmarks towards reasoning problems with context in English language/cultures. In this work, we introduce the Multilingual Native Reasoning Challenge ( MultiNRC), a benchmark designed to assess LLMs on more than 1,000 native, linguistic and culturally grounded reasoning questions written by native speakers in French, Spanish, and Chinese. MultiNRC covers four core reasoning categories: language-specific linguistic reasoning, wordplay & riddles, cultural/tradition reasoning, and math reasoning with cultural relevance. For cultural/tradition reasoning and math reasoning with cultural relevance, we also provide English equivalent translations of the multilingual questions by manual translation from native speakers fluent in English. This set of English equivalents can provide a direct comparison of LLM reasoning capacity in other languages vs. English on the same reasoning questions. We systematically evaluate current 14 leading LLMs covering most LLM families on MultiNRC and its English equivalent set. The results show that (1) current LLMs are still not good at native multilingual reasoning, with none scoring above 50% on MultiNRC; (2) LLMs exhibit distinct strengths and weaknesses in handling linguistic, cultural, and logical reasoning tasks; (3) Most models perform substantially better in math reasoning in English compared to in original languages (+10%), indicating persistent challenges with culturally grounded knowledge.

Human decision-making in high-stakes domains often relies on expertise and heuristics, but is vulnerable to hard-to-detect cognitive biases that threaten fairness and long-term outcomes. This work presents a novel approach to enhancing complex decision-making workflows through the integration of hierarchical learning alongside various enhancements. Focusing on university admissions as a representative high-stakes domain, we propose BGM-HAN, an enhanced Byte-Pair Encoded, Gated Multi-head Hierarchical Attention Network, designed to effectively model semi-structured applicant data. BGM-HAN captures multi-level representations that are crucial for nuanced assessment, improving both interpretability and predictive performance. Experimental results on real admissions data demonstrate that our proposed model significantly outperforms both state-of-the-art baselines from traditional machine learning to large language models, offering a promising framework for augmenting decision-making in domains where structure, context, and fairness matter. Source code is available at: https://github.com/junhua/bgm-han.

This study investigates the extent to which the Visual Entailment (VE) task serves as a reliable probe of vision-language understanding in multimodal language models, using the LLaMA 3.2 11B Vision model as a test case. Beyond reporting performance metrics, we aim to interpret what these results reveal about the underlying possibilities and limitations of the VE task. We conduct a series of experiments across zero-shot, few-shot, and fine-tuning settings, exploring how factors such as prompt design, the number and order of in-context examples and access to visual information might affect VE performance. To further probe the reasoning processes of the model, we used explanation-based evaluations. Results indicate that three-shot inference outperforms the zero-shot baselines. However, additional examples introduce more noise than they provide benefits. Additionally, the order of the labels in the prompt is a critical factor that influences the predictions. In the absence of visual information, the model has a strong tendency to hallucinate and imagine content, raising questions about the model's over-reliance on linguistic priors. Fine-tuning yields strong results, achieving an accuracy of 83.3% on the e-SNLI-VE dataset and outperforming the state-of-the-art OFA-X model. Additionally, the explanation evaluation demonstrates that the fine-tuned model provides semantically meaningful explanations similar to those of humans, with a BERTScore F1-score of 89.2%. We do, however, find comparable BERTScore results in experiments with limited vision, questioning the visual grounding of this task. Overall, our results highlight both the utility and limitations of VE as a diagnostic task for vision-language understanding and point to directions for refining multimodal evaluation methods.

Geo-localization from a single image at planet scale (essentially an advanced or extreme version of the kidnapped robot problem) is a fundamental and challenging task in applications such as navigation, autonomous driving and disaster response due to the vast diversity of locations, environmental conditions, and scene variations. Traditional retrieval-based methods for geo-localization struggle with scalability and perceptual aliasing, while classification-based approaches lack generalization and require extensive training data. Recent advances in vision-language models (VLMs) offer a promising alternative by leveraging contextual understanding and reasoning. However, while VLMs achieve high accuracy, they are often prone to hallucinations and lack interpretability, making them unreliable as standalone solutions. In this work, we propose a novel hybrid geo-localization framework that combines the strengths of VLMs with retrieval-based visual place recognition (VPR) methods. Our approach first leverages a VLM to generate a prior, effectively guiding and constraining the retrieval search space. We then employ a retrieval step, followed by a re-ranking mechanism that selects the most geographically plausible matches based on feature similarity and proximity to the initially estimated coordinates. We evaluate our approach on multiple geo-localization benchmarks and show that it consistently outperforms prior state-of-the-art methods, particularly at street (up to 4.51%) and city level (up to 13.52%). Our results demonstrate that VLM-generated geographic priors in combination with VPR lead to scalable, robust, and accurate geo-localization systems.

Retrosynthesis planning, essential in organic synthesis and drug discovery, has greatly benefited from recent AI-driven advancements. Nevertheless, existing methods frequently face limitations in both applicability and explainability. Traditional graph-based and sequence-to-sequence models often lack generalized chemical knowledge, leading to predictions that are neither consistently accurate nor easily explainable. To address these challenges, we introduce RetroDFM-R, a reasoning-based large language model (LLM) designed specifically for chemical retrosynthesis. Leveraging large-scale reinforcement learning guided by chemically verifiable rewards, RetroDFM-R significantly enhances prediction accuracy and explainability. Comprehensive evaluations demonstrate that RetroDFM-R significantly outperforms state-of-the-art methods, achieving a top-1 accuracy of 65.0% on the USPTO-50K benchmark. Double-blind human assessments further validate the chemical plausibility and practical utility of RetroDFM-R's predictions. RetroDFM-R also accurately predicts multistep retrosynthetic routes reported in the literature for both real-world drug molecules and perovskite materials. Crucially, the model's explicit reasoning process provides human-interpretable insights, thereby enhancing trust and practical value in real-world retrosynthesis applications.

Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: $\text{GeAR}$ and explore its performance and limitations on the SIGIR 2025 LiveRAG Challenge.

Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these models occasionally produce outputs that contain proprietary or sensitive code snippets, raising concerns about potential non-compliant use of training data, and posing risks to privacy and intellectual property. To ensure responsible and compliant deployment of CodeLLMs, training data detection (TDD) has become a critical task. While recent TDD methods have shown promise in natural language settings, their effectiveness on code data remains largely underexplored. This gap is particularly important given code's structured syntax and distinct similarity criteria compared to natural language. To address this, we conduct a comprehensive empirical study of seven state-of-the-art TDD methods on source code data, evaluating their performance across eight CodeLLMs. To support this evaluation, we introduce CodeSnitch, a function-level benchmark dataset comprising 9,000 code samples in three programming languages, each explicitly labeled as either included or excluded from CodeLLM training. Beyond evaluation on the original CodeSnitch, we design targeted mutation strategies to test the robustness of TDD methods under three distinct settings. These mutation strategies are grounded in the well-established Type-1 to Type-4 code clone detection taxonomy. Our study provides a systematic assessment of current TDD techniques for code and offers insights to guide the development of more effective and robust detection methods in the future.