Toggle light / dark theme

Large language models (LLMs) have become a general-purpose approach to embodied artificial intelligence problem-solving. When agents need to understand the semantic nuances of their environment for efficient control, LLMs’ reasoning skills are crucial in embodied AI. Recent methods, which they refer to as “programs of thought,” use programming languages as an improved prompting system for challenging reasoning tasks. Program-of-thought prompting separates the issues into executable code segments and deals with them one at a time, unlike chain-of-thought prompting. However, the relationship between the use of programming languages and the development of LLMs’ thinking skills has yet to receive enough research. When does program-of-thought suggesting work for reasoning2 remain the crucial question?

The complexity-impacted reasoning score (CIRS), a thorough metric for the link between code reasoning stages and their effects on LLMs’ reasoning abilities, is proposed in this paper. They contend that programming languages are inherently superior to serialized natural language because of their improved modeling of complex structures. Their innate procedure-oriented logic aids in solving difficulties involving several steps in thinking. Because of this, their suggested measure assesses the code complexity from both a structural and a logical standpoint. In particular, they compute the structural complexity of code reasoning stages (rationales) using an abstract syntax tree (AST). Their method uses three AST indicators (node count, node type, and depth) to keep all structural information in AST represented as a tree, which thoroughly comprehends code structures.

Researchers from Zhejiang University, Donghai Laboratory and National University of Singapore develop a way to determine logical complexity by combining coding difficulty with cyclomatic complexity, drawing inspiration from Halsted and McCabe’s idea. Thus, it is possible to consider the code’s operators, operands, and control flow. They can explicitly calculate the logic’s complexity within the code. They discover through an empirical investigation using their suggested CIRS that present LLMs have a restricted comprehension of symbolic information like code and that not all sophisticated code data can be taught and understood by LLMs. Low-complexity code blocks lack the necessary information, but high-complexity code blocks could be too challenging for LLMs to understand. To effectively improve the reasoning abilities of LLMs, only code data with an appropriate amount of complexity (structure & logic), both basic and detailed, are needed.

In a major breakthrough, scientists have built a tool to predict the odor profile of a molecule, just based on its structure. It can identify molecules that look different but smell the same, as well as molecules that look very similar but smell totally different. The research was published in Science.

Professor Jane Parker, University of Reading, said, “Vision research has wavelength, hearing research has frequency—both can be measured and assessed by instruments. But what about ? We don’t currently have a way to measure or accurately predict the odor of a molecule, based on its .”

“You can get so far with current knowledge of the molecular structure, but eventually you are faced with numerous exceptions where the odor and structure don’t match. This is what has stumped previous models of olfaction. The fantastic thing about this new ML generated model is that it correctly predicts the odor of those exceptions.”

Following more than seven years of research, researchers at the University of Seville-IBiS (Institute of Biomedicine of Seville) have identified a new key cell type with a critical role in the developmental processes of memory and learning. This breakthrough has been published in the prestigious journal Nature Neuroscience.

The research, led jointly by the University of Seville-IBiS and Karolinska Institutet, helps to understand how neural systems with decisive functions for human behavior mature. The in-depth study highlights the role of microglia, a group of cells that has been the subject of substantial information in recent years due to its involvement in various brain pathologies such as Alzheimer’s disease.

Summary: Researchers discovered that electrical noise stimulation to the frontal part of the brain can improve mathematical learning.

The study focused on those who initially showed low levels of brain excitation towards math. Unlike in placebo groups, unlike in placebo groups, a significant improvement in math skills was observed after the application of neurostimulation. This novel approach could revolutionize personalized learning.

In a recently published article featured on the cover of the Biophysical Journal, Dr. Rafael Bernardi, assistant professor of biophysics at the Department of Physics at Auburn University, and Dr. Marcelo Melo, a postdoctoral researcher in Dr. Bernardi’s group, shed light on the transformative capabilities of the next generation of supercomputers in reshaping the landscape of biophysics.

The researchers at Auburn delve into the harmonious fusion of computational modeling and experimental , providing a perspective for a future in which discoveries are made with unparalleled precision. Rather than being mere observers, today’s biophysicists, with the aid of advanced high-performance computing (HPC), are now trailblazers who can challenge longstanding biological assumptions, illuminate intricate details, and even create new proteins or design novel molecular circuits.

One of the most important aspects discussed in their perspective article is the new ability of computational biophysicists to simulate complex that range from the subatomic to whole-cell models, in extraordinary detail.

Physicists have developed a technique to precisely align supermoiré lattices, revolutionizing the potential for next-generation moiré quantum matter.

National University of Singapore (NUS) physicists have developed a technique to precisely control the alignment of supermoiré lattices by using a set of golden rules, paving the way for the advancement of next-generation moiré quantum matter.

Supermoiré Lattices

But most deep learning models are loosely based on the brain’s inner workings. AI agents are increasingly endowed with human-like decision-making algorithms. The idea that machine intelligence could become sentient one day no longer seems like science fiction.

How could we tell if machine brains one day gained sentience? The answer may be based on our own brains.

A preprint paper authored by 19 neuroscientists, philosophers, and computer scientists, including Dr. Robert Long from the Center for AI Safety and Dr. Yoshua Bengio from the University of Montreal, argues that the neurobiology of consciousness may be our best bet. Rather than simply studying an AI agent’s behavior or responses—for example, during a chat—matching its responses to theories of human consciousness could provide a more objective ruler.