arXiv:2602.21772v2 Announce Type: replace-cross Abstract: A universal audio representation should capture fine-grained speech cues and high-level semantics for environmental sounds and music in a single encoder. Existing encoders often excel in one domain but degrade in others. We propose UniWhisper, an efficient continual multi-task training framework that casts heterogeneous audio tasks into a unified instruction […]
DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
arXiv:2603.07835v1 Announce Type: cross Abstract: Knowledge distillation from proprietary LLM APIs poses a growing threat to model providers, yet defenses against this attack remain fragmented and unevaluated. We present DistillGuard, a framework for systematically evaluating output-level defenses against LLM knowledge distillation. We introduce a taxonomy of three defense categories — output perturbation, data poisoning, and […]
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
arXiv:2603.06874v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire increased agency and human oversight diminishes. In this work, we present LieCraft: a novel evaluation framework and sandbox for measuring LLM deception that addresses key limitations of prior […]
Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
arXiv:2603.08173v1 Announce Type: cross Abstract: Quantization has become essential for the efficient deployment of speech processing systems. Although widely studied, most existing quantization methods were developed for vision and NLP architectures, while the specific challenges of audio signals remain largely overlooked. In particular, we show that audio activations can exhibit large calibration ranges, leading to […]
Not Too Short, Not Too Long: How LLM Response Length Shapes People’s Critical Thinking in Error Detection
arXiv:2603.06878v1 Announce Type: new Abstract: Large language models (LLMs) have become common decision-support tools across educational and professional contexts, raising questions about how their outputs shape human critical thinking. Prior work suggests that the amount of AI assistance can influence cognitive engagement, yet little is known about how specific properties of LLM outputs (e.g., response […]
TA-RNN-Medical-Hybrid: A Time-Aware and Interpretable Framework for Mortality Risk Prediction
arXiv:2603.08278v1 Announce Type: cross Abstract: Accurate and interpretable mortality risk prediction in intensive care units (ICUs) remains a critical challenge due to the irregular temporal structure of electronic health records (EHRs), the complexity of longitudinal disease trajectories, and the lack of clinically grounded explanations in many data-driven models. To address these challenges, we propose textitTA-RNN-Medical-Hybrid, […]
Distributed Legal Infrastructure for a Trustworthy Agentic Web
arXiv:2603.06884v1 Announce Type: new Abstract: The agentic web marks a structural transition from a human-centered information network to a digital environment populated by artificial intelligence (AI) agents that perceive, decide, and act autonomously. As delegated action unfolds at machine speed, exceeds discrete moments of human judgment, and distributes decision-making across non-human actors, existing legal frameworks […]
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
arXiv:2603.08398v1 Announce Type: cross Abstract: In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity-akin to chameleons adapting their coloration to environmental cues-that can be exposed through token-conditional generation and stabilized via reinforcement learning. Specifically, by conditioning generation on carefully selected token prefixes sampled from responses exhibiting desired behaviors, LLMs seamlessly […]
Enhancing the Detection of Coronary Artery Disease Using Machine Learning
arXiv:2603.06888v1 Announce Type: new Abstract: Coronary Artery Disease (CAD) remains a leading cause of morbidity and mortality worldwide. Early detection is critical to recover patient outcomes and decrease healthcare costs. In recent years, machine learning (ML) advancements have shown significant potential in enhancing the accuracy of CAD diagnosis. This study investigates the application of ML […]
Oracle-Guided Soft Shielding for Safe Move Prediction in Chess
arXiv:2603.08506v1 Announce Type: cross Abstract: In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinforcement learning approaches for environments such as chess require hundreds of thousands of episodes and substantial computational resources to converge. Imitation learning, on the other hand, is more […]
Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks
arXiv:2603.06902v1 Announce Type: new Abstract: While Large Language Models demonstrate immense potential as proactive Medical Agents, their real-world deployment is severely bottlenecked by data scarcity under privacy constraints. To overcome this, we propose State-Enhanced Logical-Skill Memory (SELSM), a training-free framework that distills simulated clinical trajectories into entity-agnostic operational rules within an abstract skill space. During […]
A hybrid discrete-continuum modelling approach for the interactions of the immune system with oncolytic viral infections
arXiv:2404.06459v2 Announce Type: replace Abstract: Oncolytic virotherapy, utilizing genetically modified viruses to combat cancer and trigger anti-cancer immune responses, has garnered significant attention in recent years. In our previous work arXiv:2305.12386, we developed a stochastic agent-based model elucidating the spatial dynamics of infected and uninfected cells within solid tumours. Building upon this foundation, we present […]