Explaining Digital Pathology Models via Clustering Activations

ReLaX-Net proposes a novel approach to enhance the efficiency of Physical Neural Networks (PNNs) by reusing layers. PNNs are seen as promising for future computing systems, yet they currently lag behind digital neural networks in terms of scale and performance. This research focuses on hardware-friendly weight-tying methods, addressing the challenge of slow training elements in PNNs compared to their fast dynamic components. The study aims to improve the parameter efficiency of PNNs, drawing parallels with early advancements in digital neural networks.

The paper presents a novel approach called Zero-Training Task-Specific Model Synthesis (ZS-TMS) for few-shot medical image classification. This method addresses the challenge of limited annotated datasets in medical imaging by utilizing a pre-trained generative engine to synthesize parameters for a task-specific classifier. By requiring minimal input, such as a single example image, ZS-TMS aims to enhance the efficiency of medical image analysis, particularly for rare diseases where data is scarce.

The paper discusses Zero-shot coordination (ZSC), a significant challenge in multi-agent game theory, particularly in evolving games. It emphasizes the need for agents to coordinate with previously unseen partners without fine-tuning. The study introduces Scalable Population Training (ScaPT), an efficient reinforcement learning framework that enhances zero-shot coordination by utilizing a meta-agent to manage a diverse pool of agents, addressing limitations of existing methods that focus on small populations and computational constraints.

MMaDA-Parallel is a new multimodal diffusion framework aimed at enhancing thinking-aware generation in AI models. It addresses performance degradation caused by error propagation in existing autoregressive approaches. The framework introduces ParaBench, a benchmark for evaluating text and image outputs, revealing that misalignment between reasoning and generated images contributes to performance issues. MMaDA-Parallel employs supervised finetuning and Parallel Reinforcement Learning to improve interaction between text and images throughout the denoising process.

As embodied agents navigate complex environments, the ability to perceive and track individual objects over time is crucial, particularly for tasks involving similar objects. In non-Markovian contexts, decision-making relies on object-specific histories rather than the immediate scene. Without a persistent memory of past interactions, robotic policies may falter or repeat actions unnecessarily. To address this, LIBERO-Mem is introduced as a task suite designed to test robotic manipulation under conditions of partial observability at the object level.

The study explores the scaling laws of deep neural networks in medical anatomical segmentation, revealing that larger training datasets lead to improved performance across various semantic tasks and imaging modalities. It highlights the significance of deformation-guided augmentation strategies, such as random elastic deformation and registration-guided deformation, in enhancing segmentation outcomes. The research aims to address the underexplored area of data scaling in medical imaging, proposing a novel image augmentation approach to generate diffeomorphic mappings.

Recent research highlights a new class of attacks in federated learning that compromise model interpretability without impacting accuracy. The study reveals that adversarial clients can apply small color perturbations, shifting a model's saliency maps from meaningful regions while maintaining predictions. This method, termed the Chromatic Perturbation Module, systematically creates adversarial examples by altering color contrasts, leading to persistent poisoning of the model's internal feature attributions, challenging assumptions about model reliability.

International standards for biometric identity documents require strict adherence to pose requirements, particularly the square presentation of a subject's shoulders. This paper introduces a Shoulder Presentation Evaluation (SPE) algorithm that quantifies shoulder yaw and roll using 3D coordinates from two shoulder landmarks. Evaluated on 121 portrait images, the SPE scores showed a strong correlation with human-assigned labels. The algorithm effectively identifies non-compliant samples, providing a lightweight tool for automated compliance checking.