arXiv:2604.00136v1 Announce Type: new Abstract: Production LLM serving often relies on multi-model portfolios spanning a ~530x cost range, where routing decisions trade off quality against cost. This trade-off is non-stationary: providers revise pricing, model quality can regress silently, and new…
arXiv:2604.01002v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance on video question answering, but their application to long-form videos is constrained by limited context length and computational cost, making keyframe sampling essential. Existing approaches typically…
arXiv:2604.00163v1 Announce Type: new Abstract: Epileptic seizures are neurological disorders characterized by abnormal and excessive electrical activity in the brain, resulting in recurrent seizure events. Electroencephalogram (EEG) signals are widely used for seizure diagnosis due to their ability to capture…
arXiv:2411.08687v2 Announce Type: replace Abstract: Representational similarity in neural networks is inherently scale-dependent, yet widely used metrics such as Centered Kernel Alignment (CKA) and Procrustes analysis provide only global scalar estimates. These scalars often fail to distinguish micro-scale geometric jitter…
arXiv:2604.00175v1 Announce Type: new Abstract: Postural stability during movement is fundamental to independent living, fall prevention, and overall health, particularly among older adults who experience age-related declines in balance, muscle strength, and mobility. Among daily functional activities, the Sit-to-Stand (SiSt)…
arXiv:2508.13749v3 Announce Type: replace Abstract: In this paper, we study sequential decision-making for maximizing the Sharpe ratio (SR) in a stochastic multi-armed bandit (MAB) setting. Unlike standard bandit formulations that maximize cumulative reward, SR optimization requires balancing expected return and…
arXiv:2604.00195v1 Announce Type: new Abstract: We introduce L’evy-Flows, a class of normalizing flow models that replace the standard Gaussian base distribution with L’evy process-based distributions, specifically Variance Gamma (VG) and Normal-Inverse Gaussian (NIG). These distributions naturally capture heavy-tailed behavior while…
arXiv:2601.21424v2 Announce Type: replace Abstract: Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and inefficient representations. The Gray-Wyner network, a classical concept from information theory, offers a principled framework for…
arXiv:2604.00199v1 Announce Type: new Abstract: The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled…
arXiv:2603.24639v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not leverage…
