Tootfinder

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Nanxi Li, Zhengyue Zhao, Chaowei Xiao
https://arxiv.org/abs/2508.18649 https://

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To this end, we introduce PRISM (Principled Reasoning for Integrated Safety in Multimodality), a system2-like framework that aligns VLMs by embedding a structured, safety-aware reasoning process. Our framework consists of two key components: PRISM-CoT, a dataset th…

Amplitude maximization in stable systems, Schur positivity, and some conjectures on polynomial interpolation
Dmitrii M. Ostrovskii, Pavel S. Shcherbakov
https://arxiv.org/abs/2508.13554

Amplitude maximization in stable systems, Schur positivity, and some conjectures on polynomial interpolation
For $r > 0$ and integers $t \ge n > 0$, we consider the following ``amplitude maximization'' problem: maximize the quantity $|x_t|$ over the set of complex solutions $x = (x_0, x_1, \dots)$ of all homogeneous linear difference equations of order $n$ with the roots of characteristic polynomial in the disc $\{z \in \mathbb{C}: |z| \le r\}$, and with initial values $x_0, \dots, x_{n-1}$ in the unit disc. We find that for any $t,n,r$, the maximum is attained in the case of coinc…