The paper proposes GloResNet, a lightweight 3D CNN that effectively predicts brain injury in preterm infants using T2-weighted MRI, achieving an average accuracy of 75.18%.

The paper introduces FHRFormer, a masked transformer-based autoencoder designed to accurately reconstruct missing and forecast fetal heart rate (FHR) time-series data, thereby enabling robust AI-based…

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…

The paper introduces Residualized Sparse Autoencoders (ReSAEs) to improve multi-layer interventions in transformers by training each layer on the residual activation, which better preserves cross-laye…

The paper proposes a novel Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet) network, which significantly enhances brain tumor segmentation accuracy on benchmark MRI datasets.

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budge…

The paper introduces a novel simulation strategy that integrates speckle decorrelation measures from real videos to create a photorealistic dataset, enabling a deep learning algorithm that achieves st…

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

The paper introduces a generalized zero-shot benchmark for facial age estimation that ethically excludes children's data during training, demonstrating that current state-of-the-art models fail signif…

KidsNanny is a two-stage multimodal content moderation pipeline that achieves high accuracy and efficiency in detecting child safety threats, particularly excelling in text-embedded content.

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

The paper introduces a simple, token-efficient vision-language model for generating comprehensive pathology synoptic reports from multiple whole-slide images (WSIs), achieving high performance while s…

The paper proposes a novel Generative Counterfactual Attention-guided Network (GCAN) that uses multimodal connectomes and brain atlas knowledge to provide explainable and highly accurate diagnosis of…

The paper introduces Morlet Positional Encoding (MoPE), a novel wavelet-based positional encoding that models position and locality simultaneously, outperforming standard sinusoidal and RoPE methods.