VeLU: Variance-enhanced Learning Unit for Deep Neural Networks

A new study introduces CROPKT, a framework for cross-cancer prognosis knowledge transfer using Whole-Slide Images (WSI). This approach challenges the traditional cancer-specific model by leveraging a large dataset (UNI2-h-DSS) that includes 26 different cancers, aiming to enhance prognosis predictions, especially for rare tumors.

The introduction of UCAgents, a hierarchical multi-agent framework, aims to enhance medical decision-making by enforcing unidirectional convergence through structured evidence auditing, addressing the reasoning detachment seen in Vision-Language Models (VLMs). This framework is designed to mitigate biases from single-model approaches by limiting agent interactions to targeted evidence verification, thereby improving clinical trust in AI diagnostics.

A new method called Superpixel Attack has been proposed to enhance black-box adversarial attacks in deep learning models, particularly in safety-critical applications like automated driving and face recognition. This approach utilizes superpixels instead of simple rectangles to apply perturbations, improving the effectiveness of adversarial attacks and defenses.

Recent research has introduced ReMindView-Bench, a benchmark designed to evaluate how Vision-Language Models (VLMs) construct and maintain spatial mental models across multiple viewpoints. This initiative addresses the challenges VLMs face in achieving geometric coherence and cross-view consistency in spatial reasoning tasks, which are crucial for understanding 3D environments.

The introduction of ContourDiff, a novel framework for unpaired medical image translation, aims to enhance the accuracy of translating images between modalities like Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). This framework utilizes Spatially Coherent Guided Diffusion (SCGD) to maintain anatomical fidelity, which is crucial for clinical applications such as segmentation models.

The APTx Neuron has been introduced as a novel neural computation unit that integrates non-linear activation and linear transformation into a single trainable expression, derived from the APTx activation function. This architecture eliminates the need for separate activation layers, enhancing optimization efficiency. Validation on the MNIST dataset demonstrated a test accuracy of 96.69% within 11 epochs using approximately 332K trainable parameters.

A new method for multi-view crowd counting, named WSCF-MVCC, has been proposed, which operates without the need for camera calibrations or extensive crowd annotations. This weakly-supervised approach utilizes crowd count as supervision for the single-view counting module, employing a self-supervised ranking loss to enhance accuracy.

OmniBench has been introduced as a benchmark to evaluate the performance of omni-language models (OLMs) in processing visual, acoustic, and textual inputs simultaneously, highlighting the limitations of current open-source multimodal large language models (MLLMs) in instruction-following and reasoning tasks.