arXiv:2505.02922v3 Announce Type: replace
Abstract: Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) c…
arXiv:2604.23838v1 Announce Type: new
Abstract: We present JigsawRL, a cost-efficient framework that explores Pipeline Multiplexing as a new dimension of RL parallelism. JigsawRL decomposes each pipeline into a Sub-Stage Graph that exposes the intra-s…
arXiv:2602.06542v3 Announce Type: replace
Abstract: Deep knowledge tracing models have achieved significant breakthroughs in modeling student learning trajectories. However, these architectures require substantial training time and are prone to overfi…
arXiv:2604.23933v1 Announce Type: new
Abstract: Developing robust and clinically reliable EEG biomarkers requires evaluation frameworks that explicitly address cross population generalization in multi site settings such as Parkinsons disease (PD) dete…
arXiv:2509.00747v2 Announce Type: replace-cross
Abstract: Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learning. The impetus for a paradigm shift in how hardwa…
arXiv:2604.22904v1 Announce Type: cross
Abstract: Gadoxetate disodium-enhanced MRI is essential for the detection and characterization of hepatocellular carcinoma. However, acquisition of the hepatobiliary phase (HBP) requires a prolonged post-contras…
arXiv:2604.24201v1 Announce Type: new
Abstract: Motivation: Multi-omics integration can improve cancer subtyping, but modality informativeness and noise vary across cancer types and patients. Existing graph-based methods optimize modality weights join…
arXiv:2604.24224v1 Announce Type: new
Abstract: Short-range prediction of convective precipitation from weather radar observations is essential for severe weather warnings. However, deep learning models trained with pixel-wise error metrics tend to pr…
arXiv:2604.24273v1 Announce Type: new
Abstract: The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substantial memory, computational, and energy requirements…
arXiv:2603.29957v3 Announce Type: replace-cross
Abstract: Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answer. However, this approach suffers from critical lim…