Tootfinder

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks
https://arxiv.org/abs/2510.05024

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can be expensive or infeasible, motivating methods that improve learned behavior despite an imperfect training signal. We introduce Inoculation Prompting (IP), a simple but counterintuitive technique that prevents learning of an undesired behavior by modifying training prompts to explicitly request it. For example, to ino…

For me I have two scanners for papers, pictures, negatives and slides. For floppies and ZIP disks I have an old SFF machine where I can extract all of the files and save them to USB sticks.
Friends and family knows that if they don't want the pictures to send them to me. I digitize and store them in archival quality holders in a room where the humidity is controlled and the temperature doesn't change very much. Last batch were family images that no one knew of and everyone r…

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…

kabr-tools: Automated Framework for Multi-Species Behavioral Monitoring
Jenna Kline, Maksim Kholiavchenko, Samuel Stevens, Nina van Tiel, Alison Zhong, Namrata Banerji, Alec Sheets, Sowbaranika Balasubramaniam, Isla Duporge, Matthew Thompson, Elizabeth Campolongo, Jackson Miliko, Neil Rosser, Tanya Berger-Wolf, Charles V. Stewart, Daniel I. Rubenstein
https://

kabr-tools: Automated Framework for Multi-Species Behavioral Monitoring
A comprehensive understanding of animal behavior ecology depends on scalable approaches to quantify and interpret complex, multidimensional behavioral patterns. Traditional field observations are often limited in scope, time-consuming, and labor-intensive, hindering the assessment of behavioral responses across landscapes. To address this, we present kabr-tools (Kenyan Animal Behavior Recognition Tools), an open-source package for automated multi-species behavioral monitoring. This framework in…

Multihead Finite-State Dimension
Xiang Huang, Xiaoyuan Li, Jack H. Lutz, Neil Lutz
https://arxiv.org/abs/2509.22912 https://arxiv.org/pdf/2509.22912…

Multihead Finite-State Dimension
We introduce multihead finite-state dimension, a generalization of finite-state dimension in which a group of finite-state agents (the heads) with oblivious, one-way movement rules, each reporting only one symbol at a time, enable their leader to bet on subsequent symbols in an infinite data stream. In aggregate, such a scheme constitutes an $h$-head finite state gambler whose maximum achievable growth rate of capital in this task, quantified using betting strategies called gales, determines th…

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
Yinuo Liu, Ruohan Xu, Xilong Wang, Yuqi Jia, Neil Zhenqiang Gong
https://arxiv.org/abs/2510.01354 https://…

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first comprehensive benchmark study on detecting prompt injection attacks targeting web agents. We begin by introducing a fine-grained categorization of such attacks based on the threat model. We then construct datase…

RangeSAM: Leveraging Visual Foundation Models for Range-View repesented LiDAR segmentation
Paul Julius K\"uhn, Duc Anh Nguyen, Arjan Kuijper, Holger Graf, Dieter Fellner, Saptarshi Neil Sinha
https://arxiv.org/abs/2509.15886

RangeSAM: Leveraging Visual Foundation Models for Range-View repesented LiDAR segmentation
Point cloud segmentation is central to autonomous driving and 3D scene understanding. While voxel- and point-based methods dominate recent research due to their compatibility with deep architectures and ability to capture fine-grained geometry, they often incur high computational cost, irregular memory access, and limited real-time efficiency. In contrast, range-view methods, though relatively underexplored - can leverage mature 2D semantic segmentation techniques for fast and accurate predicti…