Related papers: LoMix: Learnable Weighted Multi-Scale Logits Mixin…

High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to preserve anatomical consistency across the third dimension. We…

Multi-domain fine-tuning of large language models requires improving performance on target domains while preserving performance on constrained domains, such as general knowledge, instruction following, or safety evaluations. Existing data…

Medical image segmentation is a fundamental task in computer-aided diagnosis, requiring models that balance segmentation accuracy and computational efficiency. However, existing segmentation models often struggle to effectively capture…

We present SymPix, a special-purpose spherical grid optimized for efficient sampling of rotationally invariant linear operators. This grid is conceptually similar to the Gauss-Legendre (GL) grid, aligning sample points with iso-latitude…

Modern microscopy routinely produces gigapixel images that contain structures across multiple spatial scales, from fine cellular morphology to broader tissue organization. Many analysis tasks require combining these scales, yet most vision…

In the field of healthcare, precise skin lesion segmentation is crucial for the early detection and accurate diagnosis of skin diseases. Despite significant advances in deep learning for image processing, existing methods have yet to…

Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly challenging. Despite numerous proposals for effective methods,…

We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversity and improving…

Universal machine learning interatomic potentials (UMLIPs) offer accuracy close to first-principles calculations at a fraction of the cost, showing significant potential for large-scale material simulations. However, the fragmented UMLIPs…

Intelligently reasoning about the world often requires integrating data from multiple modalities, as any individual modality may contain unreliable or incomplete information. Prior work in multimodal learning fuses input modalities only…

Massive multiple-input multiple-output (mMIMO) technology has transformed wireless communication by enhancing spectral efficiency and network capacity. This paper proposes a novel deep learning-based mMIMO precoder to tackle the complexity…

The U-shaped architecture has emerged as a crucial paradigm in the design of medical image segmentation networks. However, due to the inherent local limitations of convolution, a fully convolutional segmentation network with U-shaped…

Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing methods typically treat all intra-layer weight modules…

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO…

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…

Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bottleneck in low label settings such as Semi-Supervised…

Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment,…

In recent years, the denoising diffusion model has achieved remarkable success in image segmentation modeling. With its powerful nonlinear modeling capabilities and superior generalization performance, denoising diffusion models have…

Skip connections are central to U-Net architectures for image denoising, but standard concatenation doubles channel dimensionality and obscures information flow, allowing uncontrolled noise transfer. We propose the Additive U-Net, which…

We introduce InfiFusion, an efficient training pipeline designed to integrate multiple domain-specialized Large Language Models (LLMs) into a single pivot model, effectively harnessing the strengths of each source model. Traditional fusion…