Tootfinder

Positioning AI Tools to Support Online Harm Reduction Practice: Applications and Design Directions
Kaixuan Wang, Jason T. Jacques, Chenxin Diao
https://arxiv.org/abs/2506.22941

Positioning AI Tools to Support Online Harm Reduction Practice: Applications and Design Directions
Access to accurate and actionable harm reduction information can directly impact the health outcomes of People Who Use Drugs (PWUD), yet existing online channels often fail to meet their diverse and dynamic needs due to limitations in adaptability, accessibility, and the pervasive impact of stigma. Large Language Models (LLMs) present a novel opportunity to enhance information provision, but their application in such a high-stakes domain is under-explored and presents socio-technical challenges…

Autonomous Vision-Aided UAV Positioning for Obstacle-Aware Wireless Connectivity
Kamran Shafafi, Manuel Ricardo, Rui Campos
https://arxiv.org/abs/2506.23190

Autonomous Vision-Aided UAV Positioning for Obstacle-Aware Wireless Connectivity
Unmanned Aerial Vehicles (UAVs) offer a promising solution for enhancing wireless connectivity and Quality of Service (QoS) in urban environments, acting as aerial Wi-Fi access points or cellular base stations. Their flexibility and rapid deployment capabilities make them suitable for addressing infrastructure gaps and traffic surges. However, optimizing UAV positions to maintain Line of Sight (LoS) links with ground User Equipment (UEs) remains challenging in obstacle-dense urban scenarios. Th…

Expressivity of bisimulation pseudometrics over analytic state spaces
Daniel Luckhardt, Harsh Beohar, Clemens Kupke
https://arxiv.org/abs/2505.23635 https:…

Expressivity of bisimulation pseudometrics over analytic state spaces
A Markov decision process (MDP) is a state-based dynamical system capable of describing probabilistic behaviour with rewards. In this paper, we view MDPs as coalgebras living in the category of analytic spaces, a very general class of measurable spaces. Note that analytic spaces were already studied in the literature on labelled Markov processes and bisimulation relations. Our results are twofold. First, we define bisimulation pseudometrics over such coalgebras using the framework of fibrations…

2-Segal sets and pseudomonoids in the bicategory of spans
Sophia E Marx, Rajan Amit Mehta
https://arxiv.org/abs/2505.22832 https://ar…

2-Segal sets and pseudomonoids in the bicategory of spans
In this survey article, we give an introduction to the notion of a 2-Segal set and prove that 2-Segal sets are equivalent to pseudomonoids in the bicategory of spans. The proof utilizes graphical techniques for 2-Segal sets and spans that should be useful in more general settings. There are procedures for obtaining an associative algebra from a 2-Segal set (satisfying finiteness conditions). We describe these procedures and give several examples of algebras arising from 2-Segal sets. Wherev…

This is quite close to a risk I spoke to someone about a couple of months ago.
Government domains might host documents containing opinions or other third-party information (consultation responses, evidence, etc) - but LLM training ingest may assume the context of the government domain and incorporate it into a government position.
> Google’s AI overview interpreted the PDF document as an official EU stance, blending the information into a response

Local well-posedness of the equations governing the motion of a fluid-filled elastic solid
Giusy Mazzone
https://arxiv.org/abs/2506.22874 https://

Local well-posedness of the equations governing the motion of a fluid-filled elastic solid
We consider the fluid-structure interaction problem of a viscous incompressible fluid contained in an elastic solid whose motion is not prescribed. The equations governing the motion of the solid are given by the Navier equations of linear elasticity, whereas the fluid motion is described by the Navier-Stokes equations. We prove that the governing equations admit a unique strong solution corresponding to non-zero initial data for the solid initial displacement and velocity, and for a fluid init…

Theories of "Sexuality" in Natural Language Processing Bias Research
Jacob Hobbs
https://arxiv.org/abs/2506.22481 https://a…

Theories of "Sexuality" in Natural Language Processing Bias Research
In recent years, significant advancements in the field of Natural Language Processing (NLP) have positioned commercialized language models as wide-reaching, highly useful tools. In tandem, there has been an explosion of multidisciplinary research examining how NLP tasks reflect, perpetuate, and amplify social biases such as gender and racial bias. A significant gap in this scholarship is a detailed analysis of how queer sexualities are encoded and (mis)represented by both NLP systems and practi…

Learn to Position -- A Novel Meta Method for Robotic Positioning
Dongkun Wang, Junkai Zhao, Yunfei Teng, Jieyang Peng, Wenjing Xue, Xiaoming Tao
https://arxiv.org/abs/2506.20445

Learn to Position -- A Novel Meta Method for Robotic Positioning
Absolute positioning accuracy is a vital specification for robots. Achieving high position precision can be challenging due to the presence of various sources of errors. Meanwhile, accurately depicting these errors is difficult due to their stochastic nature. Vision-based methods are commonly integrated to guide robotic positioning, but their performance can be highly impacted by inevitable occlusions or adverse lighting conditions. Drawing on the aforementioned considerations, a vision-free, m…

Against 'softmaxing' culture
Daniel Mwesigwa
https://arxiv.org/abs/2506.22968 https://arxiv.org/pdf/2506.22968

Against 'softmaxing' culture
AI is flattening culture. Evaluations of "culture" are showing the myriad ways in which large AI models are homogenizing language and culture, averaging out rich linguistic differences into generic expressions. I call this phenomenon "softmaxing culture," and it is one of the fundamental challenges facing AI evaluations today. Efforts to improve and strengthen evaluations of culture are central to the project of cultural alignment in large AI systems. This position paper argues that machine lea…

Memory as a Service (MaaS): Rethinking Contextual Memory as Service-Oriented Modules for Collaborative Agents
Haichang Li
https://arxiv.org/abs/2506.22815 …

Memory as a Service (MaaS): Rethinking Contextual Memory as Service-Oriented Modules for Collaborative Agents
This position paper aims to rethink the role and design of memory in Large Language Model (LLM)-based agent systems. We observe that while current memory practices have begun to transcend the limitations of single interactions, they remain conceptually grounded in "bound memory" in terms of design concept-where memory is treated as local state attached to specific context or entities, forming "memory silos" that impede cross-entity collaboration. To overcome this architectural bottleneck, this …