Tootfinder

Mitigating Modal Imbalance in Multimodal Reasoning
Chen Henry Wu, Neil Kale, Aditi Raghunathan
https://arxiv.org/abs/2510.02608 https://arxiv.org/pdf/2510.…

Mitigating Modal Imbalance in Multimodal Reasoning
Foundation models (FMs) deployed in real-world tasks such as computer-use agents must integrate diverse modalities. How good are FMs at performing joint reasoning, simultaneously reasoning over multiple modalities, especially when the modalities interact and relate to each other to form cross-modal context? To better understand this problem, we study FMs on cross-modal conflicts: scenarios where conflicting evidence is presented across modalities. This allows us to examine whether FMs prioritiz…

Chief Justice John Roberts,
who has used his position to do Trump a lot of favors,
noted that Trump’s use of IEEPA to claim an unlimited tariff authority ran up against the separation of powers.
Tariffs are “taxes on Americans, and that has always been the core power of Congress,” he said.
Justice Neil Gorsuch, likewise a reliable pro-Trump vote, worried that gifting Trump a vast power to impose tariffs would be a “one-way ratchet toward the gradual but continual ac…

On tariffs, the Supreme Court's GOP justices appear ready to save Trump from himself
The administration's economic recklessness threatens Republicans' grip on power.

¡Es real! Geddy Lee y Alex Lifeson regresan con gira de Rush
De acuerdo a lo que informa RollingStone, ya hay varias fechas confirmadas en norteamerica entre junio y septiembre del próximo año. La baterista que acompañarš el dúo serš Anika Nilles.
Ojalš que extiendan la gira y bajen a sudamerica también.

BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
Caelin Kaplan, Alexander Warnecke, Neil Archibald
https://arxiv.org/abs/2510.11823 https://

BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
AI models are being increasingly integrated into real-world systems, raising significant concerns about their safety and security. Consequently, AI red teaming has become essential for organizations to proactively identify and address vulnerabilities before they can be exploited by adversaries. While numerous AI red teaming tools currently exist, practitioners face challenges in selecting the most appropriate tools from a rapidly expanding landscape, as well as managing complex and frequently c…

shakey forensics: attempting to pin down the dates neil young wrote & recorded "like a hurricane" https://drive.google.com/file/d/1j8Oa8vWbSg1GhI8UHizmcBW6FlS9bwap/view

NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning
Neil C. Janwani, Varun Madabushi, Maegan Tucker
https://arxiv.org/abs/2510.11542 https…

NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning
Reinforcement learning (RL) has emerged as a powerful method to learn robust control policies for bipedal locomotion. Yet, it can be difficult to tune desired robot behaviors due to unintuitive and complex reward design. In comparison, offline trajectory optimization methods, like Hybrid Zero Dynamics, offer more tuneable, interpretable, and mathematically grounded motion plans for high-dimensional legged systems. However, these methods often remain brittle to real-world disturbances like exter…

from my link log —
The disappearance and return to print of John M. Ford.
https://slate.com/culture/2019/11/john-ford-science-fiction-fantasy-books.html
saved 2019-11-16

The Resurrection of the Greatest Sci-Fi Writer You’ve Never Read
He was beloved by Neil Gaiman and Robert Jordan, and so good that he won a World Fantasy Award for a Christmas card. How did John M. Ford disappear?

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…