Tootfinder

Under constant attack, Ukraine’s arms makers take shelter in European factories: https://benborges.xyz/2025/07/21/under-constant-attack-ukraines-arms.html

"Medicina mental e medicina orgânica no jovem Foucault: considerações em torno de René Leriche" agora nos Arquivos HAL
#filosofia

BLIPs: Bayesian Learned Interatomic Potentials
Dario Coscia, Pim de Haan, Max Welling
https://arxiv.org/abs/2508.14022 https://arxiv.org/pdf/2508.14022

BLIPs: Bayesian Learned Interatomic Potentials
Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry. However, like most deep learning models, MLIPs struggle to make accurate predictions on out-of-distribution data or when trained in a data-scarce regime, both common scenarios in simulation-based chemistry. Moreover, MLIPs do not provide uncertainty estimates by construction, which are fundamental to guide active learning pipelines and to ensure the accuracy of simulation results compared …

Ari Shapiro will leave NPR in September after a decade as host of All Things Considered, says it "has nothing to do with the challenges facing public radio" (Tess Patton/The Wrap)
https://www.thewrap.com/ari-shapiro-exits-npr-all-things-considered-host/

Ari Shapiro to Exit NPR at End of September After 25 Years
"The work of public radio is more important today than it has ever been. I intend to continue supporting it," the "All Things Considered" host says

from my link log —
Square theory and unparalleled misalignments in American-style crosswords.
https://aaronson.org/blog/square-theory
saved 2025-05-27

Square Theory
The story starts in Crosscord, the crossword Discord server. Over 5,000 users strong, the server has emerged as a central hub for the online crossword community, a buzzing, sometimes overwhelming, sometimes delightful town square where total noobs, veteran constructors, and champion solvers alike come together to talk about words that cross each other.

Comparison between the first Steklov eigenvalue and algebraic connectivity on trees
Huiqiu Lin, Da Zhao
https://arxiv.org/abs/2508.13466 https://arxiv.org/…

Comparison between the first Steklov eigenvalue and algebraic connectivity on trees
Trees can be regarded as discrete analogue of Hadamard manifolds, namely simply-connected Riemannian manifolds of non-positive sectional curvature. In this paper, we compare the first (non-trivial) Steklov eigenvalue and algebraic connectivity of trees with prescribed number of boundary vertices and matching number. It is particularly noteworthy that while the extremal trees coincide for both operators, their corresponding eigenvalues differ significantly.

Action-Constrained Imitation Learning
Chia-Han Yeh, Tse-Sheng Nan, Risto Vuorio, Wei Hung, Hung-Yen Wu, Shao-Hua Sun, Ping-Chun Hsieh
https://arxiv.org/abs/2508.14379 https://…

Action-Constrained Imitation Learning
Policy learning under action constraints plays a central role in ensuring safe behaviors in various robot control and resource allocation applications. In this paper, we study a new problem setting termed Action-Constrained Imitation Learning (ACIL), where an action-constrained imitator aims to learn from a demonstrative expert with larger action space. The fundamental challenge of ACIL lies in the unavoidable mismatch of occupancy measure between the expert and the imitator caused by the actio…

Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Daniel Daza, Alberto Bernardi, Luca Costabello, Christophe Gueret, Masoud Mansoury, Michael Cochez, Martijn Schut
https://arxiv.org/abs/2508.13663

Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Methods for query answering over incomplete knowledge graphs retrieve entities that are likely to be answers, which is particularly useful when such answers cannot be reached by direct graph traversal due to missing edges. However, existing approaches have focused on queries formalized using first-order-logic. In practice, many real-world queries involve constraints that are inherently vague or context-dependent, such as preferences for attributes or related categories. Addressing this gap, we …

C-DOG: Training-Free Multi-View Multi-Object Association in Dense Scenes Without Visual Feature via Connected {\delta}-Overlap Graphs
Yung-Hong Sun, Ting-Hung Lin, Jiangang Chen, Hongrui Jiang, Yu Hen Hu
https://arxiv.org/abs/2507.14095

C-DOG: Training-Free Multi-View Multi-Object Association in Dense Scenes Without Visual Feature via Connected δ-Overlap Graphs
Multi-view multi-object association is a fundamental step in 3D reconstruction pipelines, enabling consistent grouping of object instances across multiple camera views. Existing methods often rely on appearance features or geometric constraints such as epipolar consistency. However, these approaches can fail when objects are visually indistinguishable or observations are corrupted by noise. We propose C-DOG, a training-free framework that serves as an intermediate module bridging object detecti…

Cross-Modality Controlled Molecule Generation with Diffusion Language Model
Yunzhe Zhang, Yifei Wang, Khanh Vinh Nguyen, Pengyu Hong
https://arxiv.org/abs/2508.14748 https://

Cross-Modality Controlled Molecule Generation with Diffusion Language Model
Current SMILES-based diffusion models for molecule generation typically support only unimodal constraint. They inject conditioning signals at the start of the training process and require retraining a new model from scratch whenever the constraint changes. However, real-world applications often involve multiple constraints across different modalities, and additional constraints may emerge over the course of a study. This raises a challenge: how to extend a pre-trained diffusion model not only t…