Tootfinder

Federal officials prevented two members of Congress on Sunday from entering an immigration detention facility in Manhattan
where the representatives were seeking to investigate reports of overcrowding, stifling heat and migrants sleeping on bathroom floors.
The representatives,
Adriano Espaillat and
Nydia Velšzquez, both Democrats from New York,
said officials at the Jacob K. Javits Federal Building had denied them access to the 10th-floor detention area because…

2 New York Representatives Are Denied Access to ICE Facility
Representatives Adriano Espaillat and Nydia Velázquez were turned away when seeking to inspect a migrant detention area inside a Manhattan federal building.

paris_transportation: Paris Transportation (2016)
A multiplex transportation network of Ile-de-France, jointly representing the road network, train network, and subway network. Nodes are intersections, rail stations or metro stations. Different modes of transportation are given by different layers. Within-layer edges represent direct transference by a particular mode of transportation, and between-layer edges represent the conjunction of those layers at that node.
This network ha…

You won't want to miss today's Metacurity for the most critical infosec developments you might have missed over the weekend, including
--Trump cyber EO reverses some parts of Biden, Obama orders
--Starlink endangers WH security,
--Nigeria convicts Chinese cybercriminals,
--US sentences Nigerian hacker,
--ICE arrests Oz hacker,
--Italy ends contract with spyware company Paragon,
--Supreme Ct. gives DOGE social security data,
--BADBOX 2.0 …

Trump cyber EO reverses some parts of Biden, Obama orders
Starlink endangers WH security, Nigeria convicts Chinese cybercriminals, US sentences Nigerian hacker, ICE arrests Oz hacker, Italy ends contract with spyware company Paragon, Supreme Ct. gives DOGE our social security data, BADBOX 2.0 infects 1m+ devices, EU issues cyber blueprint, much more

Scientists Show Reforestation Helps Cool the Planet Even More Than Thought - Slashdot
https://news.slashdot.org/story/25/06/09/0427208/scientists-show-reforestation-helps-cool-the-planet-even-more-than-thought

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
Jonathan Yang, Chuyuan Kelly Fu, Dhruv Shah, Dorsa Sadigh, Fei Xia, Tingnan Zhang
https://arxiv.org/abs/2506.06196

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as…

Regional, Lattice and Logical Representations of Neural Networks
Sandro Preto (Federal University of ABC, Brazil), Marcelo Finger (University of Sao Paulo, Brazil)
https://arxiv.org/abs/2506.05834

Regional, Lattice and Logical Representations of Neural Networks
A possible path to the interpretability of neural networks is to (approximately) represent them in the regional format of piecewise linear functions, where regions of inputs are associated to linear functions computing the network outputs. We present an algorithm for the translation of feedforward neural networks with ReLU activation functions in hidden layers and truncated identity activation functions in the output layer. We also empirically investigate the complexity of regional representati…

Employing Discrete Fourier Transform in Representational Learning
Raoof HojatJalali, Edmondo Trentin
https://arxiv.org/abs/2506.06765 https://

Employing Discrete Fourier Transform in Representational Learning
Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using autoencoders to extract latent representations at the network's compression point. These representations are valuable because they retain essential information necessary for reconstructing the original input from the compressed latent space. In this paper, we propose an…

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
Muhammed Ustaomeroglu, Guannan Qu
https://arxiv.org/abs/2506.06179

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in multi-agent reinforcement learning to alleles in genetic sequences, and show that a single layer linear self-attention can efficiently represent, learn, and generalize functions capturing pairwise interactions, including out-of-distribution scenarios. Our analysis r…

Torus knots in adjoint representation and Vogel's universality
Liudmila Bishler, Andrei Mironov
https://arxiv.org/abs/2506.06219 https://

Torus knots in adjoint representation and Vogel's universality
Vogel's universality gives a unified description of the adjoint sector of representation theory for simple Lie algebras in terms of three parameters $α,β,γ$, which are homogeneous coordinates of Vogel's plane. It is associated with representation theory within the framework of Chern-Simons theory only, and gives rise to universal knot invariants. We extend the list of these latter further, and explain how to deal with the adjoint invariants for the torus knots $T[m,n]$ considering the case o…

stanford_web: Webgraph (Stanford)
The web graph of Stanford University (stanford.edu), as collected in 2002. Nodes represent pages and directed edges represent hyperlinks between them.
This network has 281904 nodes and 2312497 edges.
Tags: Informational, Web graph, Unweighted
https://networks.skewed.de/net/s…