Related papers: MoRE: Batch-Robust Multi-Omics Representations fro…

Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the…

Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task.…

Large multimodal Mixture-of-Experts (MoEs) effectively scale the model size to boost performance while maintaining fixed active parameters. However, previous works primarily utilized full-precision experts during sparse up-cycling. Despite…

Cancer survival prediction requires integrating pathological Whole Slide Images (WSIs) and genomic profiles, a challenging task due to the inherent heterogeneity and the complexity of modeling both inter- and intra-modality interactions.…

Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on vector-level split and merge operations that introduce…

Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose…

Integrating the different data modalities of cancer patients can significantly improve the predictive performance of patient survival. However, most existing methods ignore the simultaneous utilization of rich semantic features at different…

Sparsely activated Mixture-of-Experts (MoE) models effectively increase the number of parameters while maintaining consistent computational costs per token. However, vanilla MoE models often suffer from limited diversity and specialization…

Optimal transport (OT) is a powerful geometric tool used to compare and align probability measures following the least effort principle. Despite its widespread use in machine learning (ML), OT problem still bears its computational burden,…

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…

Parametric model order reduction (pMOR) is a powerful tool for accelerating finite element (FE) simulations while maintaining parametric dependencies. For geometric parameters, pMOR by matrix interpolation is a well-suited approach because…

Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency efforts typically target either parameter sharing or adaptive…

Data-centric ML pipelines extend traditional machine learning (ML) pipelines -- of feature transformations and ML model training -- by outer loops for data cleaning, augmentation, and feature engineering to create high-quality input data.…

Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front…

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…

Purpose: To develop a self-supervised scan-specific deep learning framework for reconstructing accelerated multiparametric quantitative MRI (qMRI). Methods: We propose REFINE-MORE (REference-Free Implicit NEural representation with MOdel…

The integration of multi-modal Magnetic Resonance Imaging (MRI) and clinical data holds great promise for enhancing the diagnosis of neurological disorders (NDs) in real-world clinical settings. Deep Learning (DL) has recently emerged as a…

Accurate protein function prediction requires integrating heterogeneous intrinsic signals (e.g., sequence and structure) with noisy extrinsic contexts (e.g., protein-protein interactions and GO term annotations). However, two key challenges…

Existing machine learning methods for molecular (e.g., gene) embeddings are restricted to specific tasks or data modalities, limiting their effectiveness within narrow domains. As a result, they fail to capture the full breadth of gene…

Radiological analysis increasingly benefits from pretrained visual representations that can support heterogeneous downstream tasks across imaging modalities. In this work, we introduce OmniRad, a self-supervised radiological foundation…