New research tackles the problem of artificial intelligence ‘imagining’ details not actually present in videos, a crucial step toward reliable multimodal AI systems.
New research demonstrates that explicitly accounting for unpredictable market factors can significantly improve portfolio performance, but requires a nuanced approach to model risk.
A new approach reframes agent self-improvement as the reliable accumulation of skills, focusing on verifiable evidence and controlled generalization.
A new multi-agent framework dynamically optimizes computational resources to boost revenue in large-scale recommender systems.
![The study demonstrates that incorporating a novel regularization term [latex]\mathcal{L\_{\texttt{cor}}} [/latex] into the adversarial training of evidential models effectively improves robustness against perturbations.](https://arxiv.org/html/2512.23753v1/Images/Resubm/Adv/oct_30_evid_adv_eps_.050_kl_1.0.png)
A new approach tackles vanishing gradients in evidential deep learning, improving uncertainty estimates and overall model performance.
![The analysis demonstrates that, under the established parameters, the utility function reaches its optimum when [latex]\lambda \approx 3.1[/latex], indicating a specific value maximizes the defined benefit.](https://arxiv.org/html/2512.24371v1/x5.png)
This review explores how to achieve optimal trading strategies for derivative contracts when faced with real-world capital constraints and uncertainty in valuation models.
New research leverages process mining techniques to analyze network traffic from online games, revealing insights into player behavior and network dynamics.
As large language models become increasingly powerful, ensuring the accuracy of their responses is paramount, and a new framework offers a promising solution for detecting fabricated information.
Researchers demonstrate a novel method for generating subtle, yet effective, adversarial examples by manipulating the internal attention mechanisms of large language models.
Researchers are exploring how the unpredictable behavior of rogue waves can be used to build more efficient and powerful optical spiking neural networks.