Tootfinder

SecInfer: Preventing Prompt Injection via Inference-time Scaling
Yupei Liu, Yanting Wang, Yuqi Jia, Jinyuan Jia, Neil Zhenqiang Gong
https://arxiv.org/abs/2509.24967 https://

SecInfer: Preventing Prompt Injection via Inference-time Scaling
Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited effectiveness against strong attacks. In this work, we propose \emph{SecInfer}, a novel defense against prompt injection attacks built on \emph{inference-time scaling}, an emerging paradigm that boosts LLM capability by allocating more compute resources for reasoning dur…

Optical Design Pathways to Fluidic Space-Assembled Reflectors & Dual-Configuration Spectrographs for Characterizing Exo-Earths
Enrico Biancalani, Edward Balaban, Ruslan Belikov, Eduardo Bendek, Valeri Frumkin, Israel Gabay, Guangjun Gao, Qian Gong, Christine Gregg, Tyler Groff, Joseph Howard, Omer Luria, Michael McElwain, Lee Mundy, Rachel Ticknor, Sylvain Veilleux, Neil Zimmerman

Optical Design Pathways to Fluidic Space-Assembled Reflectors & Dual-Configuration Spectrographs for Characterizing Exo-Earths
$\textbf{Fluidic Telescopes}$ | We present a conceptual framework for optically designing space-assembled telescopes whose primary mirror is formed $\textit{in situ}$ via the enabling, scale-invariant technology of fluidic shaping. In-space assembly of optical reflectors can solve light-gathering aperture scaling, which currently limits space-borne optical telescopes. Our compass reduces the top-level optical design trade to three types of avenues -- a fluidic pathway, a legacy one buildin…

Meek Models Shall Inherit the Earth
Hans Gundlach, Jayson Lynch, Neil Thompson
https://arxiv.org/abs/2507.07931 https://arxiv.org/pdf…

Meek Models Shall Inherit the Earth
The past decade has seen incredible scaling of AI systems by a few companies, leading to inequality in AI model performance. This paper argues that, contrary to prevailing intuition, the diminishing returns to compute scaling will lead to a convergence of AI model capabilities. In other words, meek models (those with limited computation budget) shall inherit the earth, approaching the performance level of the best models overall. We develop a model illustrating that under a fixed-distribution n…

Inferring Mbh-Mbulge Evolution from the Gravitational Wave Background
Cayenne Matt, Kayhan Gultekin, Luke Kelley, Laura Blecha, Joseph Simon, Gabriella Agazie, Akash Anumarlapudi, Anne Archibald, Zaven Arzoumanian, Jeremy Baier, Paul Baker, Bence B\'ecsy, Adam Brazier, Paul Brook, Sarah Burke-Spolaor, Rand Burnette, Robin Case, James Casey-Clyde, Maria Charisi, Shami Chatterjee, Tyler Cohen, James Cordes, Neil Cornish, Fronefield Crawford, H. Thankful Cromartie, Kathryn Crowter, Me…

Inferring Mbh-Mbulge Evolution from the Gravitational Wave Background
We test the impact of an evolving supermassive black hole (SMBH) mass scaling relation (Mbh-Mbulge) on the predictions for the gravitational wave background (GWB). The observed GWB amplitude is 2-3 times higher than predicted by astrophysically informed models which suggests the need to revise the assumptions in those models. We compare a semi-analytic model's ability to reproduce the observed GWB spectrum with a static versus evolving-amplitude Mbh-Mbulge relation. We additionally consider the…