Numerous medical systems powered by Large Language Models (LLMs) have achieved remarkable progress in diverse healthcare tasks. However, research on their medication safety remains limited due to the lack of real world datasets, constrained by privacy and accessibility issues. Moreover, evaluation of LLMs in realistic clinical consultation settings, particularly regarding medication safety, is still underexplored. To address these gaps, we propose a framework that simulates and evaluates clinical consultations to systematically assess the medication safety capabilities of LLMs. Within this framework, we generate inquiry diagnosis dialogues with embedded medication risks and construct a dedicated medication safety database, RxRisk DB, containing 6,725 contraindications, 28,781 drug interactions, and 14,906 indication-drug pairs. A two-stage filtering strategy ensures clinical realism and professional quality, resulting in the benchmark RxSafeBench with 2,443 high-quality consultation scenarios. We evaluate leading open-source and proprietary LLMs using structured multiple choice questions that test their ability to recommend safe medications under simulated patient contexts. Results show that current LLMs struggle to integrate contraindication and interaction knowledge, especially when risks are implied rather than explicit. Our findings highlight key challenges in ensuring medication safety in LLM-based systems and provide insights into improving reliability through better prompting and task-specific tuning. RxSafeBench offers the first comprehensive benchmark for evaluating medication safety in LLMs, advancing safer and more trustworthy AI-driven clinical decision support.

SRAM Processing-in-Memory (PIM) has emerged as the most promising implementation for high-performance PIM, delivering superior computing density, energy efficiency, and computational precision. However, the pursuit of higher performance necessitates more complex circuit designs and increased operating frequencies, which exacerbate IR-drop issues. Severe IR-drop can significantly degrade chip performance and even threaten reliability. Conventional circuit-level IR-drop mitigation methods, such as back-end optimizations, are resource-intensive and often compromise power, performance, and area (PPA). To address these challenges, we propose AIM, comprehensive software and hardware co-design for architecture-level IR-drop mitigation in high-performance PIM. Initially, leveraging the bit-serial and in-situ dataflow processing properties of PIM, we introduce Rtog and HR, which establish a direct correlation between PIM workloads and IR-drop. Building on this foundation, we propose LHR and WDS, enabling extensive exploration of architecture-level IR-drop mitigation while maintaining computational accuracy through software optimization. Subsequently, we develop IR-Booster, a dynamic adjustment mechanism that integrates software-level HR information with hardware-based IR-drop monitoring to adapt the V-f pairs of the PIM macro, achieving enhanced energy efficiency and performance. Finally, we propose the HR-aware task mapping method, bridging software and hardware designs to achieve optimal improvement. Post-layout simulation results on a 7nm 256-TOPS PIM chip demonstrate that AIM achieves up to 69.2% IR-drop mitigation, resulting in 2.29x energy efficiency improvement and 1.152x speedup.

Abstract--Autonomous navigation in unknown environments requires compact yet expressive spatial understanding under partial observability to support high-level decision making. Existing approaches struggle to balance rich contextual representation with navigation efficiency. We present MacroNav, a learning-based navigation framework featuring two key components: (1) a lightweight context encoder trained via multi-task self-supervised learning to capture multi-scale, navigation-centric spatial representations; and (2) a reinforcement learning policy that seamlessly integrates these representations with graph-based reasoning for efficient action selection. Extensive experiments demonstrate the context encoder's efficient and robust environmental understanding. Real-world deployments further validate MacroNav's effectiveness, yielding significant gains over state-of-the-art navigation methods in both Success Rate (SR) and Success weighted by Path Length (SPL), while maintaining low computational cost. Code will be released upon acceptance.

The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and comparability across studies challenging, hindering meaningful progress. To address these issues, we introduce AdversariaLLM, a toolbox for conducting LLM jailbreak robustness research. Its design centers on reproducibility, correctness, and extensibility. The framework implements twelve adversarial attack algorithms, integrates seven benchmark datasets spanning harmfulness, over-refusal, and utility evaluation, and provides access to a wide range of open-weight LLMs via Hugging Face. The implementation includes advanced features for comparability and reproducibility such as compute-resource tracking, deterministic results, and distributional evaluation techniques. \name also integrates judging through the companion package JudgeZoo, which can also be used independently. Together, these components aim to establish a robust foundation for transparent, comparable, and reproducible research in LLM safety.

In explainable AI, Concept Activation Vectors (CAVs) are typically obtained by training linear classifier probes to detect human-understandable concepts as directions in the activation space of deep neural networks. It is widely assumed that a high probe accuracy indicates a CAV faithfully representing its target concept. However, we show that the probe's classification accuracy alone is an unreliable measure of concept alignment, i.e., the degree to which a CAV captures the intended concept. In fact, we argue that probes are more likely to capture spurious correlations than they are to represent only the intended concept. As part of our analysis, we demonstrate that deliberately misaligned probes constructed to exploit spurious correlations, achieve an accuracy close to that of standard probes. To address this severe problem, we introduce a novel concept localization method based on spatial linear attribution, and provide a comprehensive comparison of it to existing feature visualization techniques for detecting and mitigating concept misalignment. We further propose three classes of metrics for quantitatively assessing concept alignment: hard accuracy, segmentation scores, and augmentation robustness. Our analysis shows that probes with translation invariance and spatial alignment consistently increase concept alignment. These findings highlight the need for alignment-based evaluation metrics rather than probe accuracy, and the importance of tailoring probes to both the model architecture and the nature of the target concept.

Learning from human preferences is a cornerstone of aligning machine learning models with subjective human judgments. Yet, collecting such preference data is often costly and time-consuming, motivating the need for more efficient learning paradigms. Two established approaches offer complementary advantages: RLHF scales effectively to high-dimensional tasks such as LLM fine-tuning, while PBO achieves greater sample efficiency through active querying. We propose a hybrid framework that unifies RLHF's scalability with PBO's query efficiency by integrating an acquisition-driven module into the RLHF pipeline, thereby enabling active and sample-efficient preference gathering. We validate the proposed approach on two representative domains: (i) high-dimensional preference optimization and (ii) LLM fine-tuning. Experimental results demonstrate consistent improvements in both sample efficiency and overall performance across these tasks.

Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. While standard approaches typically train policies agnostic to these variations, we investigate whether sim-to-real transfer can be improved by conditioning the policy on an estimate of the dynamics parameters -- referred to as context. To this end, we integrate a context estimation module into a DR-based RL framework and systematically compare SOTA supervision strategies. We evaluate the resulting context-aware policies in both a canonical control benchmark and a real-world pushing task using a Franka Emika Panda robot. Results show that context-aware policies outperform the context-agnostic baseline across all settings, although the best supervision strategy depends on the task. Introduction Reinforcement learning (RL) has achieved significant success in developing robot controllers capable of solving complex tasks [1]. To address these limitations, physics simulation engines are widely used as a safer and more efficient alternative for policy training. Once a policy has been trained in simulation, it is transferred to the physical robot--a process known as sim-to-real transfer [2, 1, 3]. Although promising, this paradigm is hindered by the reality or sim-to-real gap, which refers to the discrepancy between the simulated and real-world environments [4, 5].

Extracting topics from text has become an essential task, especially with the rapid growth of unstructured textual data. Most existing works rely on highly computational methods to address this challenge. In this paper, we argue that probabilistic and statistical approaches, such as topic modeling (TM), can offer effective alternatives that require fewer computational resources. TM is a statistical method that automatically discovers topics in large collections of unlabeled text; however, it produces topics as distributions of representative words, which often lack clear interpretability. Our objective is to perform topic labeling by assigning meaningful labels to these sets of words. To achieve this without relying on computationally expensive models, we propose a graph-based approach that not only enriches topic words with semantically related terms but also explores the relationships among them. By analyzing these connections within the graph, we derive suitable labels that accurately capture each topic's meaning. We present a comparative study between our proposed method and several benchmarks, including ChatGPT-3.5, across two different datasets. Our method achieved consistently better results than traditional benchmarks in terms of BERTScore and cosine similarity and produced results comparable to ChatGPT-3.5, while remaining computationally efficient. Finally, we discuss future directions for topic labeling and highlight potential research avenues for enhancing interpretability and automation.

Time series classification is a task of paramount importance, as this kind of data often arises in safety-critical applications. However, it is typically tackled with black-box deep learning methods, making it hard for humans to understand the rationale behind their output. To take on this challenge, we propose a novel approach, STELLE (Signal Temporal logic Embedding for Logically-grounded Learning and Explanation), a neuro-symbolic framework that unifies classification and explanation through direct embedding of trajectories into a space of temporal logic concepts. By introducing a novel STL-inspired kernel that maps raw time series to their alignment with predefined STL formulae, our model jointly optimises accuracy and interpretability, as each prediction is accompanied by the most relevant logical concepts that characterise it. This yields (i) local explanations as human-readable STL conditions justifying individual predictions, and (ii) global explanations as class-characterising formulae. Experiments demonstrate that STELLE achieves competitive accuracy while providing logically faithful explanations, validated on diverse real-world benchmarks.

Recent advances in computational methods for designing biological sequences have sparked the development of metrics to evaluate these methods performance in terms of the fidelity of the designed sequences to a target distribution and their attainment of desired properties. However, a single software library implementing these metrics was lacking. In this work we introduce seqme, a modular and highly extendable open-source Python library, containing model-agnostic metrics for evaluating computational methods for biological sequence design. seqme considers three groups of metrics: sequence-based, embedding-based, and property-based, and is applicable to a wide range of biological sequences: small molecules, DNA, ncRNA, mRNA, peptides and proteins. The library offers a number of embedding and property models for biological sequences, as well as diagnostics and visualization functions to inspect the results. seqme can be used to evaluate both one-shot and iterative computational design methods.