CAMformer: Associative Memory is All You Need

The introduction of DinoLizer, a model based on DINOv2, aims to enhance the localization of manipulated regions in generative inpainting. By utilizing a pretrained DINOv2 model on the B-Free dataset, it incorporates a linear classification head to predict manipulations at a granular patch resolution, employing a sliding-window strategy for larger images. This method shows superior performance compared to existing local manipulation detectors across various datasets.

LLaVA-UHD v3 has been introduced as a new multi-modal large language model (MLLM) that utilizes Progressive Visual Compression (PVC) for efficient native-resolution encoding, enhancing visual understanding capabilities while addressing computational overhead. This model integrates refined patch embedding and windowed token compression to optimize performance in vision-language tasks.

A new model named SMARC has been introduced, enabling surface material reconstruction and classification from minimal visual cues, specifically using just a 10% contiguous patch of an image. This approach addresses the limitations of existing methods that require dense observations, making it particularly useful in constrained environments.

A new automated histopathologic assessment framework for Hirschsprung Disease has been developed using a multi-stage Vision Transformer approach. This framework effectively segments the muscularis propria, delineates the myenteric plexus, and identifies ganglion cells, achieving a Dice coefficient of 89.9% and a Plexus Inclusion Rate of 100% across 30 whole-slide images with expert annotations.

A recent study has introduced a modular, on-site solution for sustainable nutrient management in agriculture, utilizing lightweight anomaly detection techniques to optimize nutrient consumption and enhance crop growth. The approach employs a tiered pipeline for status estimation and anomaly detection, integrating multispectral imaging and an autoencoder for early warnings during nutrient depletion experiments.

A new method for classifying glioblastoma subregions using a contrastive learning-based encoder has been developed, achieving notable performance metrics in the BraTS-Path 2025 Challenge. The model, which fine-tunes a pre-trained Vision Transformer, secured second place with an MCC of 0.6509 and an F1-score of 0.5330 on the final test set.

A new framework named PeriodNet has been introduced to enhance time series forecasting by leveraging an innovative attention mechanism. This model aims to improve the analysis of both univariate and multivariate time series data through period attention and sparse period attention mechanisms, which focus on local characteristics and periodic patterns.

A recent study introduced a computational Turing test designed to evaluate the realism of text generated by large language models (LLMs) compared to human language. This framework combines aggregate metrics and interpretable linguistic features to assess how closely LLMs can mimic human language in various datasets.