arXiv:2509.11791v2 Announce Type: replace-cross Abstract: This paper investigates how the performance of visual navigation policies trained in simulation compares to policies trained with real-world data. Performance degradation of simulator-trained policies is often significant when they are evaluated in the real…
arXiv:2602.21371v1 Announce Type: new Abstract: Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention matrices, with no communication…
arXiv:2602.08786v3 Announce Type: replace-cross Abstract: Institutions increasingly use prediction to allocate scarce resources. From a design perspective, better predictions compete with other investments, such as expanding capacity or improving treatment quality. Here, the big question is not how to solve…
arXiv:2602.21372v1 Announce Type: new Abstract: Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private data, producing…
arXiv:2602.21995v1 Announce Type: cross Abstract: The optimization of complex medical appointment scheduling remains a significant operational challenge in multi-center healthcare environments, where clinical safety protocols and patient logistics must be reconciled. This study proposes and evaluates a Genetic Algorithm (GA)…
arXiv:2602.21381v1 Announce Type: new Abstract: Time series causal discovery is essential for understanding dynamic systems, yet many existing methods remain sensitive to noise, non-stationarity, and sampling variability. We propose the Validated Consensus-Driven Framework (VCDF), a simple and method-agnostic layer that…
arXiv:2602.22124v1 Announce Type: cross Abstract: Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action looping…
arXiv:2602.21390v1 Announce Type: new Abstract: We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of…
arXiv:2501.16443v2 Announce Type: replace Abstract: While deep reinforcement learning (RL) from pixels has achieved remarkable success, its sample inefficiency remains a critical limitation for real-world applications. Model-based RL (MBRL) addresses this by learning a world model to generate simulated experience,…
By leveraging idle computing time, researchers can double the speed of model training while preserving accuracy.
