arXiv:2601.14299v1 Announce Type: new Abstract: Network defenders face a steady stream of attacks, observed as raw Intrusion Detection System (IDS) alerts. The sheer volume of alerts demands prioritization, typically based on high-level risk classifications. This work expands the scope of risk measurement by examining alerts not only through their technical characteristics but also by examining and classifying their temporal patterns. One critical issue in responding to intrusion alerts is determining whether an alert is part of an escalating […]

Ver mais

arXiv:2603.09985v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet their ability to accurately assess their own confidence remains poorly understood. We present an empirical study investigating whether LLMs exhibit patterns reminiscent of the Dunning-Kruger effect — a cognitive bias where individuals with limited competence tend to overestimate their abilities. We evaluate four state-of-the-art models (Claude Haiku 4.5, Gemini 2.5 Pro, Gemini 2.5 Flash, and Kimi K2) across four benchmark datasets […]

Ver mais

arXiv:2602.06064v1 Announce Type: new Abstract: Scheduling precedence-constrained tasks under shared renewable resources is central to modern computing platforms. The Resource Investment Problem (RIP) models this setting by minimizing the cost of provisioned renewable resources under precedence and timing constraints. Exact mixed-integer programming and constraint programming become impractically slow on large instances, and dynamic updates require schedule revisions under tight latency budgets. We present iScheduler, a reinforcement-learning-driven iterative scheduling framework that formulates RIP solving as a Markov decision process […]

Ver mais

arXiv:2603.10044v1 Announce Type: new Abstract: Safety benchmarks evaluate language models in isolation, typically using multiple-choice format; production deployments wrap these models in agentic scaffolds that restructure inputs through reasoning traces, critic agents, and delegation pipelines. We report one of the largest controlled studies of scaffold effects on safety (N = 62,808; six frontier models, four deployment configurations), combining pre-registration, assessor blinding, equivalence testing, and specification curve analysis. Map-reduce scaffolding degrades measured safety (NNH = 14), yet two of […]

Ver mais

arXiv:2503.00307v4 Announce Type: replace-cross Abstract: Part of the success of diffusion models stems from their ability to perform iterative refinement, i.e., repeatedly correcting outputs during generation. However, modern masked discrete diffusion lacks this capability: when a token is generated, it cannot be updated again, even when it introduces an error. Here, we address this limitation by introducing the remasking diffusion model (ReMDM) sampler, a method that can be applied to pretrained masked diffusion models in a principled way […]

Ver mais

Hi, I’ll be doing research at Mila Quebec this summer, and I’d love some advice on how to and what to prepare. The topic is Causal models for continual reinforcement learning. More specifically, the project hypothesizes that agents whose goal is to maximize empowerment gains will construct causal models of their actions and generalize better in agentic systems. For some background, I’m a last semester McGill undergraduate majoring in Statistics and Software Eng. I’ve done courses about: -PGMs: […]

Ver mais

Byline: By focusing on one of healthcare’s most overlooked problems—documentation—Foster AI is using AI to reduce doctor burnout and quietly build India’s healthcare data foundation. Article: India’s healthcare system does not suffer from a lack of intent. It suffers from a lack of time. With a doctor-to-patient ratio of roughly 1:1600—far below the World Health Organisation’s recommended 1:1000—clinicians in public hospitals routinely see 30 to 50 patients a day. In that environment, documentation becomes the casualty. Notes are […]

Ver mais

Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen domains or label spaces. While recent advancements have transitioned toward leveraging Large Language Models (LLMs) as predictors to enhance GNNs, these methods often suffer from cross-modal alignment issues. A recent paradigm (i.e., Graph-R1) overcomes the aforementioned architectural dependencies by adopting a purely text-based format and utilizing LLM-based graph reasoning, showing improved […]

Ver mais