Tootfinder

Oh, you're experiencing or critiquing a structural problem? Have you ever considered trying to change your personal behavior instead?

While the most obvious racism is being handled by many commercial LLMs they are still full of covert racism (and other forms of discrimination). Because speech, choice of words etc. are proxies for our discriminatory structures.
It's obvious that these are structural problems of LLMs, it's good that more researchers are publishing about this.

Covert racism in LLMs
Shocking new paper with potentially serious implications

Structural origin of relaxation in dense colloidal suspensions
Ratimanasee Sahu, Mohit Sharma, Peter Schall, Sarika Maitra Bhattacharyya, Vijayakumar Chikkadi
https://arxiv.org/abs/2403.02517

Structural origin of relaxation in dense colloidal suspensions
Amorphous solids relax via slow molecular rearrangement induced by thermal fluctuations or applied stress. Although microscopic structural signatures predicting these structural relaxations have long been sought, a physically motivated structural measure relevant to diverse systems remains elusive. Here, we introduce a structural order parameter derived from the mean-field caging potential experienced by the particles due to their neighbors, which reliably predicts the occurrence of structural …

In Ukraine people can at least flee the russian advance, in Gaza there is no way out. Ordering people around to "safezones" is not a structural solution. Israel is making the textbook mistake of starting a tactical operation (Rafah) without a clear view of their strategic endgame it seems or am i missing something ?
#israel

By making a series of cuts and folds in a sheet of paper, Baker found she could produce two planes connected by a complex set of thin strips. Without the need for any adhesive like glue or tape, this pattern created a surface that was thick but lightweight. Baker named her creation Spin-Valence. Structural tests later showed that an individual tile made this way, and rendered in steel, can bear more than a thousand times its own weight.

This architect is cutting up materials to make them stronger and lighter
Emily Baker hopes her designs can make it cheaper and easier to build stuff in disaster zones or outer space.

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures
Yannick Kirchhoff, Maximilian R. Rokuss, Saikat Roy, Balint Kovacs, Constantin Ulrich, Tassilo Wald, Maximilian Zenk, Philipp Vollmuth, Jens Kleesiek, Fabian Isensee, Klaus Maier-Hein
https://arxiv.org/abs/2404.03010…

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures
Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-foc…

Model-based reinforcement learning for protein backbone design
Frederic Renard, Cyprien Courtot, Alfredo Reichlin, Oliver Bent
https://arxiv.org/abs/2405.01983

Model-based reinforcement learning for protein backbone design
Designing protein nanomaterials of predefined shape and characteristics has the potential to dramatically impact the medical industry. Machine learning (ML) has proven successful in protein design, reducing the need for expensive wet lab experiment rounds. However, challenges persist in efficiently exploring the protein fitness landscapes to identify optimal protein designs. In response, we propose the use of AlphaZero to generate protein backbones, meeting shape and structural scoring requirem…

G4-Attention: Deep Learning Model with Attention for predicting DNA G-Quadruplexes
Shrimon Mukherjee, Pulakesh Pramanik, Partha Basuchowdhuri, Santanu Bhattacharya
https://arxiv.org/abs/2403.02765

G4-Attention: Deep Learning Model with Attention for predicting DNA G-Quadruplexes
G-Quadruplexes are the four-stranded non-canonical nucleic acid secondary structures, formed by the stacking arrangement of the guanine tetramers. They are involved in a wide range of biological roles because of their exceptionally unique and distinct structural characteristics. After the completion of the human genome sequencing project, a lot of bioinformatic algorithms were introduced to predict the active G4s regions \textit{in vitro} based on the canonical G4 sequence elements, G-\textit{r…

Dual-Arm Construction Robot for Automatic Fixation of Structural Parts to Concrete Surfaces in Narrow Environments
Andr\'e Yuji Yasutomi, Toshiaki Hatano, Kanta Hamasaki, Makoto Hattori, Daisuke Matsuka
https://arxiv.org/abs/2403.19948

Dual-Arm Construction Robot for Automatic Fixation of Structural Parts to Concrete Surfaces in Narrow Environments
Fixation of structural parts to concrete is a repetitive, heavy-duty, and time-consuming task that requires automation due to the lack of skilled construction workers. Previously developed automation techniques have not achieved the complete fixation of structural parts and are difficult to implement in narrow construction environments. In this study, we propose a construction robot system that enables the complete installation of structural parts to concrete and can be easily introduced to uns…