arXiv:2604.22750v1 Announce Type: cross
Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three question…
arXiv:2604.10079v4 Announce Type: replace
Abstract: Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after convergence, models ofte…
arXiv:2604.22050v1 Announce Type: cross
Abstract: Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear …
arXiv:2502.17011v2 Announce Type: replace-cross
Abstract: Financial bond yield forecasting is challenging due to data scarcity, nonlinear macroeconomic dependencies, and evolving market conditions. In this paper, we propose a novel framework that leve…
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…
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, creatin…
arXiv:2604.22579v1 Announce Type: cross
Abstract: We study whether deep networks for medical imaging learn useful nonrobust features – predictive input patterns that are not human interpretable and highly susceptible to small adversarial perturbations…
arXiv:2509.20979v2 Announce Type: replace
Abstract: In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching syste…
arXiv:2510.12328v5 Announce Type: replace
Abstract: Accurate rainfall forecasting, particularly for extreme events, remains a significant challenge in climatology and the Earth system. This paper presents novel physics-informed Graph Neural Networks (…
arXiv:2604.22348v1 Announce Type: new
Abstract: Clinical risk prediction using longitudinal medical data supports individualized care. Self-supervised foundation models have emerged as a promising approach for leveraging large-scale unlabeled healthca…