arXiv:2505.17639v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization. We introduce PreMoE, a training-free framework that proactively compiles sparse MoE variants for targeted deployment scenarios.…
arXiv:2604.22084v1 Announce Type: new Abstract: Malware attacks have a significant negative impact on organizations of varied scales in the field of cybersecurity. Recently, malware researchers have increasingly turned to machine learning techniques to combat sophisticated obfuscation methods used in malware.…
arXiv:2509.25003v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruction error across multiple denoising…
arXiv:2604.22099v1 Announce Type: new Abstract: Dimensionality reduction is a critical preprocessing step for clustering high-dimensional data, yet comprehensive evaluation of its impact across diverse methods and data types remains limited. In this study, we systematically assess the influence of five…
arXiv:2511.21777v3 Announce Type: replace Abstract: Methane is a potent greenhouse gas, responsible for roughly 30% of warming since pre-industrial times. A small number of large point sources account for a disproportionate share of emissions, creating an opportunity for substantial reductions…
arXiv:2604.22110v1 Announce Type: new Abstract: Standard supervised classification trains models to imitate the exact labels provided by a perfect oracle. This imitation happens in a single pass, restricting the model to a fixed compute budget even when inputs vary in…
arXiv:2601.19674v2 Announce Type: replace Abstract: Ambitious decarbonisation targets are rapidly increasing the commission of new offshore wind farms. For these newly commissioned plants to run, accurate power forecasts are needed from the onset. These allow grid stability, good reserve management…
arXiv:2604.22117v1 Announce Type: new Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining creates a subtle but serious attack surface. We study Stealth Pretraining Seeding (SPS), a new attack family in which adversaries…
arXiv:2603.10093v2 Announce Type: replace Abstract: Recent 3D molecular generation methods primarily use asynchronous auto-regressive or synchronous diffusion models. While auto-regressive models build molecules sequentially, they’re limited by a short horizon and a discrepancy between training and inference. Conversely, synchronous diffusion…
arXiv:2604.22154v1 Announce Type: new Abstract: Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not indicate when a…
