Tootfinder

Finished “In My Time of Dying: How I Came Face to Face with the Idea of an Afterlife” by Sebastian Junger.
In 2020, the author nearly died from an aneurysm in his abdomen. While in the OR, as medical staff rushed to save his life, he had an extraordinary experience. The doctors and nurses all to his right, an empty void to his left, and his dead father telling him it’s OK.
Part autobiography, part scientific inquiry, all goodness.
4/5 stars ⭐️⭐️⭐️⭐️

In My Time of Dying: How I Came Face to Face with the I…
A near-fatal health emergency leads to this powerful re…

Attention's forward pass and Frank-Wolfe
Albert Alcalde, Borjan Geshkovski, Dom\`enec Ruiz-Balet
https://arxiv.org/abs/2508.09628 https://arxiv.org/pdf…

Attention's forward pass and Frank-Wolfe
We study the hardmax limit of self-attention dynamics for token embeddings obtained in the zero-temperature ($β\to+\infty$) regime, and relate it to the finite-$β$ setting. In this limit, the update rule can be viewed as a Frank-Wolfe step for a quadratic objective over the convex hull of the current token embeddings. When the key-query matrix is negative semidefinite, the method linearly contracts all tokens to a single cluster at the origin. When it is positive semidefinite, extending the h…

Masquerade: Learning from In-the-wild Human Videos using Data-Editing
Marion Lepert, Jiaying Fang, Jeannette Bohg
https://arxiv.org/abs/2508.09976 https://…

Masquerade: Learning from In-the-wild Human Videos using Data-Editing
Robot manipulation research still suffers from significant data scarcity: even the largest robot datasets are orders of magnitude smaller and less diverse than those that fueled recent breakthroughs in language and vision. We introduce Masquerade, a method that edits in-the-wild egocentric human videos to bridge the visual embodiment gap between humans and robots and then learns a robot policy with these edited videos. Our pipeline turns each human video into robotized demonstrations by (i) est…

Imagine him sitting, months on end, in an accountability circile in order to be fed. Imagine the confused expression that's basically just his annoying little face. Imagine, for a bit, that tiny face shrinking into that giant head as he listens for the 3rd month in a row to someone shows him videos of starving people in Gaza, shows him hours of surgery video from gunshot wounds he's laughed at, explains the patriarchy to him and why it was destroyed, explains to him why empathy is a good thing and is the bedrock of this new world we've created, explains why we've build a world that centeres carework above all else. Imagine the confusion and agony.
I really wanted that for him, and for every fascist. It's disappointing when they're taken early, but I can't honetly ever say that I find it sad.

¡Regresó el Fútbol Americano! Raiders empatan en Seattle https://www.raiders.com/video/regreso-el-futbol-americano-raiders-empatan-en-seattle-reporte-raiders

¡Regresó el Fútbol Americano! Raiders empatan en Seattle https://www.raiders.com/video/regreso-el-futbol-americano-raiders-empatan-en-seattle-reporte-raiders

LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Fangfu Liu, Hao Li, Jiawei Chi, Hanyang Wang, Minghui Yang, Fudong Wang, Yueqi Duan
https://arxiv.org/abs/2507.02813

LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Recovering 3D structures with open-vocabulary scene understanding from 2D images is a fundamental but daunting task. Recent developments have achieved this by performing per-scene optimization with embedded language information. However, they heavily rely on the calibrated dense-view reconstruction paradigm, thereby suffering from severe rendering artifacts and implausible semantic synthesis when limited views are available. In this paper, we introduce a novel generative framework, coined LangS…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/5]:
- From Video to EEG: Adapting Joint Embedding Predictive Architecture to Uncover Visual Concepts in...
Amirabbas Hojjati, Lu Li, Ibrahim Hameed, Anis Yazidi, Pedro G. Lind, Rabindra Khadka

Gradient Electronic Landscapes in van der Waals Heterostructures
Nolan Lassaline, Camilla H. S{\o}rensen, Giulia Meucci, Sander J. Linde, Kian Latifi Yaghin, Tuan K. Chau, Damon J. Carrad, Peter B{\o}ggild, Thomas S. Jespersen, Timothy J. Booth
https://arxiv.org/abs/2508.07896

Gradient Electronic Landscapes in van der Waals Heterostructures
Two-dimensional (2D) materials such as graphene and hexagonal boron nitride (hBN) provide a versatile platform for quantum electronics. Experiments generally require encapsulating graphene within hBN flakes, forming a protective van der Waals (vdW) heterostructure that preserves delicate properties of the embedded crystal. To produce functional devices, heterostructures are typically shaped by electron beam lithography and etching, which has driven progress in 2D materials research. However, pa…

Unsupervised Video Continual Learning via Non-Parametric Deep Embedded Clustering
Nattapong Kurpukdee, Adrian G. Bors
https://arxiv.org/abs/2508.21773 https://

Unsupervised Video Continual Learning via Non-Parametric Deep Embedded Clustering
We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning solution for the under-explored problem of unsupervised video continual learning. Videos represent a complex and rich spatio-temporal media information, widely used in many applications, but which have not been sufficiently explored in unsupervised continual learning. Prior studies have only focus…