Artificial neural networks (ANNs) have become the de facto standard for modeling the human visual system, primarily due to their success in predicting neural responses. However, with many models now achieving similar predictive accuracy, we need a stronger criterion. Here, we use small-scale adversarial probes to characterize the local representational geometry of many highly predictive ANN-based brain models. We report four key findings. First, we show that most contemporary ANN-based brain models are unexpectedly fragile. Despite high prediction scores, their response predictions are highly sensitive to small, imperceptible perturbations, revealing unreliable local coding directions. Second, we demonstrate that a model's sensitivity to adversarial probes can better discriminate between candidate neural encoding models than prediction accuracy alone. Third, we find that standard models rely on distinct local coding directions that do not transfer across model architectures. Finally, we show that adversarial probes from robusti-fied models produce generalizable and semantically meaningful changes, suggesting that they capture the local coding dimensions of the visual system. Together, our work shows that local representational geometry provides a stronger criterion for brain model evaluation. We also provide empirical grounds for favoring robust models, whose more stable coding axes not only align better with neural selectivity but also generate concrete, testable predictions for future experiments. For over a decade, NeuroAI has celebrated artificial neural networks (ANNs) for how well they predict brain responses (Y amins et al., 2014; Kriegeskorte, 2015; Storrs et al., 2021; Zhuang et al., 2021; Doerig et al., 2023). However, the field now faces a new challenge: a diverse array of ANN models predict data equally well, making it nearly impossible to distinguish between them using accuracy alone (Schrimpf et al., 2018; Conwell et al., 2023; Linsley et al., 2023; Ratan Murty et al., 2021).

Physics-Informed Neural Networks (PINNs) leverage machine learning with differential equations to solve direct and inverse problems, ensuring predictions follow physical laws. Physiologically based pharmacokinetic (PBPK) modeling advances beyond classical compartmental approaches by using a mechanistic, physiology focused framework. A PBPK model is based on a system of ODEs, with each equation representing the mass balance of a drug in a compartment, such as an organ or tissue. These ODEs include parameters that reflect physiological, biochemical, and drug-specific characteristics to simulate how the drug moves through the body. In this paper, we introduce PBPK-iPINN, a method to estimate drug-specific or patient-specific parameters and drug concentration profiles in PBPK brain compartment models using inverse PINNs. We demonstrate that, for the inverse problem to converge to the correct solution, the loss function components (data loss, initial conditions loss, and residual loss) must be appropriately weighted, and parameters (including number of layers, number of neurons, activation functions, learning rate, optimizer, and collocation points) must be carefully tuned. The performance of the PBPK-iPINN approach is then compared with established traditional numerical and statistical methods.

-- Electroencephalography (EEG) is a non-invasive method for measuring brain activity with high temporal resolution; however, EEG signals often exhibit low signal-to-noise ratios because of contamination from physiological and environmental artifacts. One of the major challenges hindering the real-world deployment of brain-computer interfaces (BCIs) involves the frequent occurrence of motion-related EEG artifacts. Most prior studies on EEG motion artifact removal rely on single-modality approaches, such as Artifact Subspace Reconstruction (ASR) and Independent Component Analysis (ICA), without incorporating simultaneously recorded modalities like inertial measurement units (IMUs), which directly capture the extent and dynamics of motion. This work proposes a fine-tuned large brain model (LaBraM)-based correlation attention mapping method that leverages spatial channel relationships in IMU data to identify motion-related artifacts in EEG signals. The fine-tuned model contains approximately 9.2 million parameters and uses 5.9 hours of EEG and IMU recordings for training, just 0.2346% of the 2500 hours used to train the base model. We compare our results against the established ASR-ICA benchmark across varying time scales and motion activities, showing that incorporating IMU reference signals significantly improves robustness under diverse motion scenarios.

Decoding visual stimuli from neural activity is essential for understanding the human brain. While fMRI methods have successfully reconstructed static images, fMRI-to-video reconstruction faces challenges due to the need for capturing spatiotemporal dynamics like motion and scene transitions. Recent approaches have improved semantic and perceptual alignment but struggle to integrate coarse fMRI data with detailed visual features. Inspired by the hierarchical organization of the visual system, we propose NEURONS, a novel framework that decouples learning into four correlated sub-tasks: key object segmentation, concept recognition, scene description, and blurry video reconstruction. This approach simulates the visual cortex's functional specialization, allowing the model to capture diverse video content. In the inference stage, NEURONS generates robust conditioning signals for a pre-trained text-to-video diffusion model to reconstruct the videos. Extensive experiments demonstrate that NEURONS outperforms state-of-the-art baselines, achieving solid improvements in video consistency (26.6%) and semantic-level accuracy (19.1%). Notably, NEURONS shows a strong functional correlation with the visual cortex, highlighting its potential for brain-computer interfaces and clinical applications. Code and model weights will be available at: https://github.com/xmed-lab/NEURONS.

Summary: Researchers created a new human brain model using machine learning-based optimization of required user profile information. We all like to think that we know ourselves best, but, given that our brain activity is largely governed by our subconscious mind, it is probably our brain that knows us better! While this is only a hypothesis, researchers from Japan have already proposed a content recommendation system that assumes this to be true. Essentially, such a system makes use of its user's brain signals (acquired using, say, an MRI scan) when exposed to particular content and eventually, by exploring various users and contents, builds up a general model of brain activity. "Once we obtain the'ultimate' brain model, we should be able to perfectly estimate the brain activity of a person exposed to a specific content," says Prof. Ryoichi Shinkuma from Shibaura Institute of Technology, Japan, who was a part of the team that came up with the idea.

The Helmholtz International BigBrain Analytics and Learning Laboratory (HIBALL) is a collaboration between McGill University and Forschungszentrum Jülich to develop next-generation high-resolution human brain models using cutting-edge Machine- and Deep Learning methods and high-performance computing. HIBALL is based on the high-resolution BigBrain model first published by the Jülich and McGill teams in 2013. Over the next five years, the lab will be funded with a total of up to 6 million Euro by the German Helmholtz Association, Forschungszentrum Jülich, and Healthy Brains, Healthy Lives at McGill University. In 2003, when Jülich neuroscientist Katrin Amunts and her Canadian colleague Alan Evans began scanning 7,404 histological sections of a human brain, it was completely unclear whether it would ever be possible to reconstruct this brain on the computer in three dimensions. At that time, there were no technical possibilities to cope with the huge amount of data.

This paper suggests a statistical framework for describing the relations between the physical and conceptual entities of a brain-like model. In particular, features and concept instances are put into context. This may help with understanding or implementing a similar model. The paper suggests that features are in fact the wiring. With this idea, the actual length of the connection is important, because it is related to neuron synchronization. The paper then suggests that the concepts are neuron-based and firing neurons are concept instances. Therefore, features become the static framework of the interconnected neural system and concepts are combinations of these, as determined by an external stimulus and the neural associations. Along with this statistical model, it is possible to propose a simplified design for the neuron itself, but based on the idea that it can vary its input and output signals. Some test results also help to support the theory.

Bee brains have evolved to be so energy efficient that they may be able to count using only four nerve cells, scientists have found. Simulations with a brain model used just four nerve cells and found this simplistic organ would be able to count up to, and beyond, five. The small number of nerve cells needed to count indicates that brain size is not as important as brain organisation, scientists claim. Bee brains have evolved to be so energy efficient that they can count using only four brain cells, scientists have found. Simulations showed the simple brain was capable of counting small quantities by closely studying one item at a time.

For years, marketers have talked about brands as having personalities. Now they have the tools to bring those brands to life – virtually at least. Rapid developments in artificial intelligence (AI) are being combined with Academy Award-winning animation skills to create virtual humans that are the closest yet to flesh and blood. And for brands, that offers the opportunity to put a very human-looking face on a corporate body. One of the latest iterations of these virtual humans comes from Auckland-based company, Soul Machines, whose co-founder and CEO, Mark Sagar's ground-breaking work in computer-generated faces on films, King Kong and Avatar, was recognised with consecutive Oscars.