Tootfinder

Non-Normal Eigenvector Amplification in Multi-Dimensional Kesten Processes
Virgile Troude, Didier Sornette
https://arxiv.org/abs/2510.11763 https://arxiv.o…

Non-Normal Eigenvector Amplification in Multi-Dimensional Kesten Processes
Heavy-tailed fluctuations and power law statistics pervade physics, finance, and economics, yet their origin is often ascribed to systems poised near criticality. Here we show that such behavior can emerge far from instability through a universal mechanism of non-normal eigenvector amplification in multidimensional Kesten processes $x_{t+1}=A_t x_t+η_t$, where $A_t$ are random interaction matrices and $η_t$ represents external inputs, capturing the evolving interdependence among $N$ coupled c…

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning
Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan
https://arxiv.org/abs/2510.08567

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning
Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge with a vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning. …

Docs and interviews: Media Matters is struggling to survive, having racked up ~$15M in legal fees to defend itself from lawsuits by Elon Musk, the FTC, and AGs (New York Times)
https://www.nytimes.com/2025/07/25/us/poli

Under Siege From Trump and Musk, a Top Liberal Group Falls Into Crisis
Scrambling to pay legal fees, Media Matters has dialed back its criticism, trimmed its staff and contemplated closing entirely.

Under Siege From Trump and Musk, a Top Liberal Group Falls Into Crisis (New York Times)
https://www.nytimes.com/2025/07/25/us/politics/media-matters-musk-crisis.html?unlocked_article_code=1.ZE8.uS77.aCoRbTwphEFY&smid=url-share
http://www.memeorandum.com/250725/p57#a250725p57

Classifying Wavelet Coorbit Spaces in Dimension 2
Noufal Asharaf, Hartmut F\"uhr, Vaishakh Jayaprakash
https://arxiv.org/abs/2508.04521 https://arxiv.…

Classifying Wavelet Coorbit Spaces in Dimension 2
Coorbit spaces provide a rigorous framework for the assessment of the approximation theoretic properties of generalized wavelet systems. It is therefore useful to understand when two different wavelet systems give rise to the same scales of coorbit spaces. This paper provides an exhaustive answer to this question for the case of continuous wavelet transforms associated with matrix groups in dimension two.

GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance & Stealthy Attacks on AI
Joshua Kalyanapu, Farshad Dizani, Darsh Asher, Azam Ghanbari, Rosario Cammarota, Aydin Aysu, Samira Mirbagher Ajorpaz
https://arxiv.org/abs/2507.17033

GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance & Stealthy Attacks on AI
As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions (AMX) is one such example, debuting on the 4th generation Intel Xeon Scalable CPU. We discover a timing side and covert channel, GATEBLEED, caused by the aggressive power gating utilized to keep the CPU within operating limits. We show that the GATEBLEED side channel is a threat to AI privacy as many ML models such as transform…