Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with identical architecture, they meet challenges when dealing with Multimodal Large Language Models (MLLMs) with inherent heterogeneous property, including differences in model architecture and the asymmetry in the parameter space. In this work, we propose AdaMMS1, a novel model merging method tailored for heterogeneous MLLMs. Our method tackles the challenges in three steps: mapping, merging and searching. Specifically, we first design mapping function between models to apply model merging on MLLMs with different architecture. Then we apply linear interpolation on model weights to actively adapt the asymmetry in the heterogeneous MLLMs. Finally in the hyper-parameter searching step, we propose an unsupervised hyper-parameter selection method for model merging. As the first model merging method capable of merging heterogeneous MLLMs without labeled data, extensive experiments on various model combinations demonstrated that AdaMMS outperforms previous model merging methods on various vision-language benchmarks.2

Diffusion models have recently emerged as a state-of-the-art approach for synthetic Electronic Health Record (EHR) generation, offering superior fidelity and diversity over traditional generative models. However, existing diffusion-based methods struggle with unique challenges: limited representation learning and modality utilization, where they fail to explicitly capture inter-modality dependencies and fine-grained code-level interactions, and constrained adaptability due to reliance on U-Net-based architectures, which are not well-suited for handling the heterogeneous and evolving nature of EHR data. Furthermore, current evaluation paradigms rely on either perplexity-based sequence modeling or global distributional measures, lacking robustness in assessing both intra-visit code relationships and inter-visit temporal patterns. To address these limitations, we propose MedDiTPro, a diffusion transformer-based framework that enhances multimodal EHR generation by integrating structured modality-aware guidance. Through a unified transformer for intra-visit representation learning, a modality-specific and datawise prompt learner, and a diffusion transformer with structured guidance, MedDiTPro achieves state-of-the-art performance in generating diverse and clinically meaningful synthetic records. Extensive experiments on publicly available datasets demonstrate that MedDiTPro achieves state-of-the-art fidelity, privacy preservation, and utility.

re-training (MEDCSP), a new pre-training strategy designed to bridge the gap between multimodal medical sources. MEDCSP employs modality-level aggregation to unify patient data within individual sources. Additionally, leveraging temporal information and diagnosis history, MEDCSP effectively captures explicit and implicit correlations between patients across different sources. To evaluate the proposed strategy, we conduct comprehensive experiments, where the experiments are based on 6 modalities from 2 real-world medical data sources, and MEDCSP is evaluated on 4 tasks against 19 baselines, marking an initial yet essential step towards cross-source modeling in the medical domain.

Automatic International Classification of Diseases (ICD) coding plays a crucial role in the extraction of relevant information from clinical notes for proper recording and billing. One of the most important directions for boosting the performance of automatic ICD coding is modeling ICD code relations. However, current methods insufficiently model the intricate relationships among ICD codes and often overlook the importance of context in clinical notes. In this paper, we propose a novel approach, a contextualized and flexible framework, to enhance the learning of ICD code representations. Our approach, unlike existing methods, employs a dependent learning paradigm that considers the context of clinical notes in modeling all possible code relations. We evaluate our approach on six public ICD coding datasets and the experimental results demonstrate the effectiveness of our approach compared to state-of-the-art baselines.

Foundation models have demonstrated remarkable capabilities in handling diverse modalities and tasks, outperforming conventional artificial intelligence (AI) approaches that are highly task-specific and modality-reliant.In the medical domain, however, the development of comprehensive foundation models is constrained by limited access to diverse modalities and stringent privacy regulations.To address these constraints, this study introduces a novel knowledge injection approach, FED-KIM, designed to scale the medical foundation model within a federated learning framework.FEDKIM leverages lightweight local models to extract healthcare knowledge from private data and integrates this knowledge into a centralized foundation model using a designed adaptive Multitask Multimodal Mixture Of Experts (M 3 OE) module.This method not only preserves privacy but also enhances the model's ability to handle complex medical tasks involving multiple modalities.Our extensive experiments across twelve tasks in seven modalities demonstrate the effectiveness of FEDKIM in various settings, highlighting its potential to scale medical foundation models without direct access to sensitive data.

Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.

Synthesizing electronic health records (EHR) data has become a preferred strategy to address data scarcity, improve data quality, and model fairness in healthcare. However, existing approaches for EHR data generation predominantly rely on state-of-the-art generative techniques like generative adversarial networks, variational autoencoders, and language models. These methods typically replicate input visits, resulting in inadequate modeling of temporal dependencies between visits and overlooking the generation of time information, a crucial element in EHR data. Moreover, their ability to learn visit representations is limited due to simple linear mapping functions, thus compromising generation quality. To address these limitations, we propose a novel EHR data generation model called EHRPD. It is a diffusion-based model designed to predict the next visit based on the current one while also incorporating time interval estimation. To enhance generation quality and diversity, we introduce a novel time-aware visit embedding module and a pioneering predictive denoising diffusion probabilistic model (P-DDPM). Additionally, we devise a predictive U-Net (PU-Net) to optimize P-DDPM. We conduct experiments on two public datasets and evaluate EHRPD from fidelity, privacy, and utility perspectives. The experimental results demonstrate the efficacy and utility of the proposed EHRPD in addressing the aforementioned limitations and advancing EHR data generation.

This study introduces the Federated Medical Knowledge Injection (FedMEKI) platform, a new benchmark designed to address the unique challenges of integrating medical knowledge into foundation models under privacy constraints. By leveraging a cross-silo federated learning approach, FedMEKI circumvents the issues associated with centralized data collection, which is often prohibited under health regulations like the Health Insurance Portability and Accountability Act (HIPAA) in the USA. The platform is meticulously designed to handle multi-site, multi-modal, and multi-task medical data, which includes 7 medical modalities, including images, signals, texts, laboratory test results, vital signs, input variables, and output variables. The curated dataset to validate FedMEKI covers 8 medical tasks, including 6 classification tasks (lung opacity detection, COVID-19 detection, electrocardiogram (ECG) abnormal detection, mortality prediction, sepsis protection, and enlarged cardiomediastinum detection) and 2 generation tasks (medical visual question answering (MedVQA) and ECG noise clarification). This comprehensive dataset is partitioned across several clients to facilitate the decentralized training process under 16 benchmark approaches. FedMEKI not only preserves data privacy but also enhances the capability of medical foundation models by allowing them to learn from a broader spectrum of medical knowledge without direct data exposure, thereby setting a new benchmark in the application of foundation models within the healthcare sector.

Health risk prediction aims to forecast the potential health risks that patients may face using their historical Electronic Health Records (EHR). Although several effective models have developed, data insufficiency is a key issue undermining their effectiveness. Various data generation and augmentation methods have been introduced to mitigate this issue by expanding the size of the training data set through learning underlying data distributions. However, the performance of these methods is often limited due to their task-unrelated design. To address these shortcomings, this paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. Furthermore, MedDiffusion discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data. Experimental evaluation on four real-world medical datasets demonstrates that MedDiffusion outperforms 14 cutting-edge baselines in terms of PR-AUC, F1, and Cohen's Kappa. We also conduct ablation studies and benchmark our model against GAN-based alternatives to further validate the rationality and adaptability of our model design. Additionally, we analyze generated data to offer fresh insights into the model's interpretability. The source code is available via https://shorturl.at/aerT0.

Session-based recommendation aims to predict intents of anonymous users based on their limited behaviors. Modeling user behaviors involves two distinct rationales: co-occurrence patterns reflected by item IDs, and fine-grained preferences represented by item modalities (e.g., text and images). However, existing methods typically entangle these causes, leading to their failure in achieving accurate and explainable recommendations. To this end, we propose a novel framework DIMO to disentangle the effects of ID and modality in the task. DIMO aims to disentangle these causes at both item and session levels. At the item level, we introduce a co-occurrence representation schema to explicitly incorporate co-occurrence patterns into ID representations. Simultaneously, DIMO aligns different modalities into a unified semantic space to represent them uniformly. At the session level, we present a multi-view self-supervised disentanglement, including proxy mechanism and counterfactual inference, to disentangle ID and modality effects without supervised signals. Leveraging these disentangled causes, DIMO provides recommendations via causal inference and further creates two templates for generating explanations. Extensive experiments on multiple real-world datasets demonstrate the consistent superiority of DIMO over existing methods. Further analysis also confirms DIMO's effectiveness in generating explanations.

Predicting adverse drug reactions (ADRs) of drugs is one of the most critical steps in drug development. By pre-estimating the adverse reactions, researchers and drug development companies can greatly prevent the potential ADR risks and tragedies. However, the current ADR prediction methods suffer from several limitations. First, the prediction results are based on pure drug-related information, which makes them impossible to be directly applied for the personalized ADR prediction task. The lack of personalization of models also makes rare adverse events hard to be predicted. Therefore, it is of great interest to develop a new personalized ADR prediction method by introducing additional sources, e.g., patient health records. However, few methods have tried to use additional sources. In the meantime, the variety of different source formats and structures makes this task more challenging. To address the above challenges, we propose a novel personalized multi-sourced-based drug adverse reaction prediction model named pADR. pADR first works on every single source to transform them into proper representations. Next, a hierarchical multi-sourced Transformer is designed to automatically model the interactions between different sources and fuse them together for the final adverse event prediction. Experimental results on a new multi-sourced ADR prediction dataset show that PADR outperforms state-of-the-art drug-based baselines. Moreover, the case and ablation studies also illustrate the effectiveness of our proposed fusion strategies and the reasonableness of each module design.

Pretraining has proven to be a powerful technique in natural language processing (NLP), exhibiting remarkable success in various NLP downstream tasks. However, in the medical domain, existing pretrained models on electronic health records (EHR) fail to capture the hierarchical nature of EHR data, limiting their generalization capability across diverse downstream tasks using a single pretrained model. To tackle this challenge, this paper introduces a novel, general, and unified pretraining framework called MedHMP, specifically designed for hierarchically multimodal EHR data. The effectiveness of the proposed MedHMP is demonstrated through experimental results on eight downstream tasks spanning three levels. Comparisons against eighteen baselines further highlight the efficacy of our approach.

Massive Open Online Courses (MOOCs), offering a new way to study online, are revolutionizing education. One challenging issue in MOOCs is how to design effective and fine-grained course concepts such that students with different backgrounds can grasp the essence of the course. In this paper, we conduct a systematic investigation of the problem of course concept extraction for MOOCs. We propose to learn latent representations for candidate concepts via an embedding-based method. Moreover, we develop a graph-based propagation algorithm to rank the candidate concepts based on the learned representations. We evaluate the proposed method using different courses from XuetangX and Coursera. Experimental results show that our method significantly outperforms all the alternative methods (+0.013-0.318 in terms of R-precision; p<<0.01, t-test).