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

Sequential recommendation models have been widely adopted for modeling user behavior. Existing approaches typically construct user interaction sequences by sorting items according to timestamps and then model user preferences from…

Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information. Recently, CIL based on pre-trained models (PTMs) has achieved…

Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still…

Parallel imaging is ubiquitous in MRI, enabling diverse applications such as ultra-high-resolution functional and quantitative imaging with greater temporal resolution or reduced scan times respectively. Successful unfolding is contingent…

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Adapting large-scale foundation models in multi-task scenarios often suffers from task conflict and oblivion. To mitigate such issues, we propose a novel ''model MoE-ization'' strategy that leads to a conflict- and oblivion-resistant…

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into…

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Recent advancements in multimodal pre-training models have significantly advanced computational pathology. However, current approaches predominantly rely on visual-language models, which may impose limitations from a molecular perspective…

Multimodal emotion recognition in conversation (MERC) requires representations that effectively integrate signals from multiple modalities. These signals include modality-specific cues, information shared across modalities, and interactions…

The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models demands significantly larger datasets and computational…

Whole-body biometric recognition is a challenging multimodal task that integrates various biometric modalities, including face, gait, and body. This integration is essential for overcoming the limitations of unimodal systems. Traditionally,…

Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning. However, significant challenges remain: (1) Simply increasing the rank size of LoRA does not effectively capture high-rank information, which leads…

Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…

Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a…

Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning methods require that all the modalities used for training are…

The Mixture-of-Experts (MoE) architecture has become a predominant paradigm for scaling large language models (LLMs). Despite offering strong performance and computational efficiency, large MoE-based LLMs like DeepSeek-V3-0324 and…

Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…

We introduce MORPH, a modality-agnostic, autoregressive foundation model for partial differential equations (PDEs). MORPH is built on a convolutional vision transformer backbone that seamlessly handles heterogeneous spatiotemporal datasets…

Multimodal remote sensing classification often suffers from missing modalities caused by sensor failures and environmental interference, leading to severe performance degradation. In this work, we rethink missing-modality learning from a…