April 2026

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) can become a single point of failure when it fails to penalize unsafe behaviors. While existing red-teaming approaches primarily target policy-level weaknesses, they overlook what we term systemic weaknesses cases where both the core LLM and the RM fail in tandem. We present ARES, a framework that systematically […]

Ver mais

arXiv:2604.18788v1 Announce Type: new Abstract: Apple Neural Engine (ANE) is a dedicated neural processing unit (NPU) present in every Apple Silicon chip. Mixture-of-Experts (MoE) LLMs improve inference efficiency via sparse activation but are challenging for NPUs in three ways: expert routing is unpredictable and introduces dynamic tensor shapes that conflict with the shape-specific constraints of NPUs; several irregular operators, e.g., top-k, scatter/gather, etc., are not NPU-friendly; and launching many small expert kernels incurs substantial dispatch and synchronization overhead. […]

Ver mais

arXiv:2604.18786v1 Announce Type: new Abstract: Scientific feasibility assessment asks whether a claim is consistent with established knowledge and whether experimental evidence could support or refute it. We frame feasibility assessment as a diagnostic reasoning task in which, given a hypothesis, a model predicts feasible or infeasible and justifies its decision. We evaluate large language models (LLMs) under controlled knowledge conditions (hypothesis-only, with experiments, with outcomes, or both) and probe robustness by progressively removing portions of the experimental and/or […]

Ver mais

arXiv:2604.18781v1 Announce Type: new Abstract: Large-scale automated morphometric analysis of brain MRI is limited by the thick-slice, anisotropic acquisitions prevalent in routine clinical practice. Existing generative super-resolution (SR) methods produce visually compelling isotropic volumes but often introduce anatomical hallucinations, systematic volumetric overestimation, and structural distortions that compromise downstream quantitative analysis and diagnostic safety. To address this, we propose CAHAL (Clinically Applicable resolution enHAncement for Low-resolution MRI scans), a hallucination-robust, physics-informed resolution enhancement framework that operates directly in the […]

Ver mais

arXiv:2604.18780v1 Announce Type: new Abstract: Semi-Markov Conditional Random Fields (semi-CRFs) assign labels to segments of a sequence rather than to individual positions, enabling exact inference over segment-level features and principled uncertainty estimates at their boundaries. However, existing implementations must materialize a large edge potential tensor whose size grows with sequence length, maximum segment length, and label count, becoming prohibitive for speech-scale state spaces and intractable at genomic scales where sequences can exceed 100,000 positions. This memory bottleneck has […]

Ver mais

arXiv:2604.18779v1 Announce Type: new Abstract: Existing web agents typically initiate exploration from the root URL, which is inefficient for complex websites with deep hierarchical structures. Without a global view of the website’s structure, agents frequently fall into navigation traps, explore irrelevant branches, or fail to reach target information within a limited budget. We propose Mango, a multi-agent web navigation method that leverages the website structure to dynamically determine optimal starting points. We formulate URL selection as a multi-armed […]

Ver mais

arXiv:2604.18776v1 Announce Type: new Abstract: Structural reliability evaluation for composites constitutes a fundamentally high-dimensional multiscale problem, as microscale material uncertainties must propagate to the macroscale and can be quantified as high-dimensional random fields. Conventional approaches are computationally intractable, as they rely on repeatedly solving coupled partial differential equation systems across scales while contending with the exponential complexity inherent in high-dimensional uncertainty quantification. This work introduces a scalable and physically consistent framework that addresses both bottlenecks simultaneously in the […]

Ver mais

arXiv:2604.18775v1 Announce Type: new Abstract: Detecting jailbreak behaviour in large language models remains challenging, particularly when strongly aligned models produce harmful outputs only rarely. In this work, we present an empirical study of output based jailbreak detection under realistic conditions using the JailbreakBench Behaviors dataset and multiple generator models with varying alignment strengths. We evaluate both a lexical TF-IDF detector and a generation inconsistency based detector across different sampling budgets. Our results show that single output evaluation systematically […]

Ver mais

arXiv:2604.18771v1 Announce Type: new Abstract: We present a computational study of diffusion synthetic acceleration (DSA) for the monoenergetic, isotropically scattering $S_N$ transport equations, discretised in space by a polytopic discontinuous Galerkin method. Using a discrete ordinates angular discretisation, we construct the DSA correction with an interior-penalty diffusion operator and compare a classical symmetric interior penalty (SIP) formulation with a modified interior penalty (MIP) variant, together with homogeneous Dirichlet and Marshak (Robin) diffusion boundary conditions imposed weakly in the […]

Ver mais

arXiv:2604.18770v1 Announce Type: new Abstract: Translating business problems into well-specified machine learning solutions is a prerequisite for successful AI systems, yet this upstream translation is still one of the least supported steps in existing methodologies. We conduct a structured narrative literature review of 18 approaches spanning requirements engineering (RE), machine learning (ML) project management, and automation. We organize these approaches into a taxonomy of four families and compare them across six input artifact categories, six output artifact categories, […]

Ver mais