arXiv:2605.12623v1 Announce Type: cross
Abstract: Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We introduce DocAtlas, a…
arXiv:2605.12743v1 Announce Type: cross
Abstract: Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through (i) sophisticated phy…
arXiv:2603.29475v2 Announce Type: replace
Abstract: Survival analysis is crucial for many medical applications, but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular covariates. While the …
arXiv:2604.13986v2 Announce Type: replace
Abstract: Predicting the effects of perturbations in-silico on cell state can identify drivers of cell behavior at scale and accelerate drug discovery. However, modeling challenges remain due to the inherent h…
arXiv:2605.08541v2 Announce Type: replace
Abstract: Neural scaling laws approximate a language model’s loss as a power-law function of parameter count $N$ and token count $D$. Following Chinchilla-style compute-optimal training, many studies fit scali…
arXiv:2605.10896v2 Announce Type: replace
Abstract: Corporate bankruptcy prediction is a high-stakes financial task characterized by severe class imbalance and multi-horizon forecasting demands. Public datasets supporting it remain scarce and small: w…
arXiv:2605.11405v2 Announce Type: replace
Abstract: Data curation has shifted the quality-compute frontier for language-model and contrastive image-text pretraining, but its role for vision-language models (VLMs) is far less established. We ask how fa…
arXiv:2605.12862v1 Announce Type: cross
Abstract: In production Wide-Area Networks (WANs), correlated failures dominate availability losses, forcing operators to reserve large safety margins that leave substantial capacity underutilized. Achieving hig…
arXiv:2605.12992v1 Announce Type: cross
Abstract: Neural population models, which predict the joint firing of many simultaneously recorded neurons forward in time, are typically evaluated by a single aggregate Pearson correlation $r$ between predicted…
arXiv:2605.12999v1 Announce Type: cross
Abstract: Closed-loop brain-computer interfaces often require both a forecast of upcoming neural population activity and a readout of the animal’s behavioral state. A single Mamba forecaster, trained only on nex…