arXiv:2603.26829v1 Announce Type: new Abstract: Language models detect false premises when asked directly but absorb them under conversational pressure, producing authoritative professional output built on errors they already identified. This failure – order-gap hallucination – is invisible to output inspection…
arXiv:2603.27936v1 Announce Type: cross Abstract: Nonlinear Partial Differential Equations (PDEs) are ubiquitous in mathematical physics and engineering. Although Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving PDE problems, they typically struggle to identify multiple distinct solutions,…
arXiv:2603.26830v1 Announce Type: new Abstract: As large language models (LLMs) continue to improve and see further integration into software systems, so does the need to understand the conditions in which they will perform. We contribute a statistical framework for understanding…
arXiv:2603.28342v1 Announce Type: cross Abstract: We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe. On the agent side, Kernel-Smith maintains a population of executable candidates…
arXiv:2603.26839v1 Announce Type: new Abstract: How do multimodal models solve visual spatial tasks — through genuine planning, or through brute-force search in token space? We introduce textsc{MazeBench}, a benchmark of 110 procedurally generated maze images across nine controlled groups, and…
arXiv:2106.00839v3 Announce Type: replace Abstract: When AI systems make errors in high-stakes domains like medical diagnosis or autonomous vehicles, a single algorithmic flaw across varying operational contexts can generate highly heterogeneous losses that challenge traditional insurance assumptions. Algorithmic insurance constitutes…
arXiv:2603.26841v1 Announce Type: new Abstract: We present FatigueFormer, a semi-end-to-end framework that deliberately combines saliency-guided feature separation with deep temporal modeling to learn interpretable and generalizable muscle fatigue dynamics from surface electromyography (sEMG). Unlike prior approaches that struggle to maintain…
arXiv:2502.00472v3 Announce Type: replace Abstract: Forecasting multiscale chaotic dynamical systems, such as turbulent flows, with deep learning remains a formidable challenge due to the spectral bias of neural networks, which hinders the accurate representation of fine-scale structures in long-term predictions.…
arXiv:2603.26842v1 Announce Type: new Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target…
arXiv:2508.02343v2 Announce Type: replace Abstract: Quantization significantly accelerates inference in large language models (LLMs) by replacing original high-precision matrices with low-precision counterparts. Recent advances in weight-activation quantization have primarily focused on mapping both weights and activations to the INT4 format.…
