BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates

Learning from multiple modalities often suffers from imbalance, where information-rich modalities dominate optimization while weaker or partially missing modalities contribute less. This imbalance becomes severe in realistic settings with imbalanced missing rates (IMR), where each modality is absent with different probabilities, distorting representation learning and gradient dynamics. We revisit this issue from a training-process perspective and propose BALM, a model-agnostic plug-in framework to achieve balanced multimodal learning under IMR. The framework comprises two complementary modules: the Feature Calibration Module (FCM), which recalibrates unimodal features using global context to establish a shared representation basis across heterogeneous missing patterns; the Gradient Rebalancing Module (GRM), which balances learning dynamics across modalities by modulating gradient magnitudes and directions from both distributional and spatial perspectives. BALM can be seamlessly integrated into diverse backbones, including multimodal emotion recognition (MER) models, without altering their architectures. Experimental results across multiple MER benchmarks confirm that BALM consistently enhances robustness and improves performance under diverse missing and imbalance settings. Code available at: https://github.com/np4s/BALM_CVPR2026.git

MissBench: Benchmarking Multimodal Affective Analysis under Imbalanced Missing Modalities

Multimodal affective computing underpins key tasks such as sentiment analysis and emotion recognition. Standard evaluations, however, often assume that textual, acoustic, and visual modalities are equally available. In real applications, some modalities are systematically more fragile or expensive, creating imbalanced missing rates and training biases that task-level metrics alone do not reveal. We introduce MissBench, a benchmark and framework for multimodal affective tasks that standardizes both shared and imbalanced missing-rate protocols on four widely used sentiment and emotion datasets. MissBench also defines two diagnostic metrics. The Modality Equity Index (MEI) measures how fairly different modalities contribute across missing-modality configurations. The Modality Learning Index (MLI) quantifies optimization imbalance by comparing modality-specific gradient norms during training, aggregated across modality-related modules. Experiments on representative method families show that models that appear robust under shared missing rates can still exhibit marked modality inequity and optimization imbalance under imbalanced conditions. These findings position MissBench, together with MEI and MLI, as practical tools for stress-testing and analyzing multimodal affective models in realistic incomplete-modality settings.For reproducibility, we release our code at: https://anonymous.4open.science/r/MissBench-4098/

Counterfactual Understanding via Retrieval-aware Multimodal Modeling for Time-to-Event Survival Prediction

This paper tackles the problem of time-to-event counterfactual survival prediction, aiming to optimize individualized survival outcomes in the presence of heterogeneity and censored data. We propose CURE, a framework that advances counterfactual survival modeling via comprehensive multimodal embedding and latent subgroup retrieval. CURE integrates clinical, paraclinical, demographic, and multi-omics information, which are aligned and fused through cross-attention mechanisms. Complex multi-omics signals can be adaptively refined using a mixture-of-experts architecture, emphasizing the most informative omics components. Building upon this representation, CURE implicitly retrieves patient-specific latent subgroups that capture both baseline survival dynamics and treatment-dependent variations. Experimental results on METABRIC and TCGA-LUAD datasets demonstrate that proposed CURE model consistently outperforms strong baselines in survival analysis, evaluated using the Time-dependent Concordance Index ($C^{td}$) and Integrated Brier Score (IBS). These findings highlight the potential of CURE to enhance multimodal understanding and serve as a foundation for future treatment recommendation models. All code and related resources are publicly available to facilitate the reproducibility https://github.com/L2R-UET/CURE.

Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation

Recommendation systems have faced significant challenges in cold-start scenarios, where new items with a limited history of interaction need to be effectively recommended to users. Though multimodal data (e.g., images, text, audio, etc.) offer rich information to address this issue, existing approaches often employ simplistic integration methods such as concatenation, average pooling, or fixed weighting schemes, which fail to capture the complex relationships between modalities. Our study proposes a novel Mixture of Experts (MoE) framework for multimodal cold-start recommendation, named MAMEX, which dynamically leverages latent representation from different modalities. MAMEX utilizes modality-specific expert networks and introduces a learnable gating mechanism that adaptively weights the contribution of each modality based on its content characteristics. This approach enables MAMEX to emphasize the most informative modalities for each item while maintaining robustness when certain modalities are less relevant or missing. Extensive experiments on benchmark datasets show that MAMEX outperforms state-of-the-art methods in cold-start scenarios, with superior accuracy and adaptability. For reproducibility, the code has been made available on Github https://github.com/L2R-UET/MAMEX.

Personalized Diffusion Model Reshapes Cold-Start Bundle Recommendation

Bundle recommendation aims to recommend a set of items to each user. However, the sparser interactions between users and bundles raise a big challenge, especially in cold-start scenarios. Traditional collaborative filtering methods do not work well for this kind of problem because these models rely on interactions to update the latent embedding, which is hard to work in a cold-start setting. We propose a new approach (DisCo), which relies on a personalized Diffusion backbone, enhanced by disentangled aspects for the user's interest, to generate a bundle in distribution space for each user to tackle the cold-start challenge. During the training phase, DisCo adjusts an additional objective loss term to avoid bias, a prevalent issue while using the generative model for top-$K$ recommendation purposes. Our empirical experiments show that DisCo outperforms five comparative baselines by a large margin on three real-world datasets. Thereby, this study devises a promising framework and essential viewpoints in cold-start recommendation. Our materials for reproducibility are available at: https://github.com/bt-nghia/DisCo.

A Dual-Module Denoising Approach with Curriculum Learning for Enhancing Multimodal Aspect-Based Sentiment Analysis

Multimodal Aspect-Based Sentiment Analysis (MABSA) combines text and images to perform sentiment analysis but often struggles with irrelevant or misleading visual information. Existing methodologies typically address either sentence-image denoising or aspect-image denoising but fail to comprehensively tackle both types of noise. To address these limitations, we propose DualDe, a novel approach comprising two distinct components: the Hybrid Curriculum Denoising Module (HCD) and the Aspect-Enhance Denoising Module (AED). The HCD module enhances sentence-image denoising by incorporating a flexible curriculum learning strategy that prioritizes training on clean data. Concurrently, the AED module mitigates aspect-image noise through an aspect-guided attention mechanism that filters out noisy visual regions which unrelated to the specific aspects of interest. Our approach demonstrates effectiveness in addressing both sentence-image and aspect-image noise, as evidenced by experimental evaluations on benchmark datasets.

TECO: Improving Multimodal Intent Recognition with Text Enhancement through Commonsense Knowledge Extraction

The objective of multimodal intent recognition (MIR) is to leverage various modalities-such as text, video, and audio-to detect user intentions, which is crucial for understanding human language and context in dialogue systems. Despite advances in this field, two main challenges persist: (1) effectively extracting and utilizing semantic information from robust textual features; (2) aligning and fusing non-verbal modalities with verbal ones effectively. This paper proposes a Text Enhancement with CommOnsense Knowledge Extractor (TECO) to address these challenges. We begin by extracting relations from both generated and retrieved knowledge to enrich the contextual information in the text modality. Subsequently, we align and integrate visual and acoustic representations with these enhanced text features to form a cohesive multimodal representation. Our experimental results show substantial improvements over existing baseline methods.

Comparative Opinion Mining in Product Reviews: Multi-perspective Prompt-based Learning

Comparative reviews are pivotal in understanding consumer preferences and influencing purchasing decisions. Comparative Quintuple Extraction (COQE) aims to identify five key components in text: the target entity, compared entities, compared aspects, opinions on these aspects, and polarity. Extracting precise comparative information from product reviews is challenging due to nuanced language and sequential task errors in traditional methods. To mitigate these problems, we propose MTP-COQE, an end-to-end model designed for COQE. Leveraging multi-perspective prompt-based learning, MTP-COQE effectively guides the generative model in comparative opinion mining tasks. Evaluation on the Camera-COQE (English) and VCOM (Vietnamese) datasets demonstrates MTP-COQE's efficacy in automating COQE, achieving superior performance with a 1.41% higher F1 score than the previous baseline models on the English dataset. Additionally, we designed a strategy to limit the generative model's creativity to ensure the output meets expectations. We also performed data augmentation to address data imbalance and to prevent the model from becoming biased towards dominant samples.

Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning

Bundle recommendation aims to enhance business profitability and user convenience by suggesting a set of interconnected items. In real-world scenarios, leveraging the impact of asymmetric item affiliations is crucial for effective bundle modeling and understanding user preferences. To address this, we present BunCa, a novel bundle recommendation approach employing item-level causation-enhanced multi-view learning. BunCa provides comprehensive representations of users and bundles through two views: the Coherent View, leveraging the Multi-Prospect Causation Network for causation-sensitive relations among items, and the Cohesive View, employing LightGCN for information propagation among users and bundles. Modeling user preferences and bundle construction combined from both views ensures rigorous cohesion in direct user-bundle interactions through the Cohesive View and captures explicit intents through the Coherent View. Simultaneously, the integration of concrete and discrete contrastive learning optimizes the consistency and self-discrimination of multi-view representations. Extensive experiments with BunCa on three benchmark datasets demonstrate the effectiveness of this novel research and validate our hypothesis.

Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition

Emotion recognition in conversation (ERC) is a crucial task in natural language processing and affective computing. This paper proposes MultiDAG+CL, a novel approach for Multimodal Emotion Recognition in Conversation (ERC) that employs Directed Acyclic Graph (DAG) to integrate textual, acoustic, and visual features within a unified framework. The model is enhanced by Curriculum Learning (CL) to address challenges related to emotional shifts and data imbalance. Curriculum learning facilitates the learning process by gradually presenting training samples in a meaningful order, thereby improving the model's performance in handling emotional variations and data imbalance. Experimental results on the IEMOCAP and MELD datasets demonstrate that the MultiDAG+CL models outperform baseline models. We release the code for MultiDAG+CL and experiments: https://github.com/vanntc711/MultiDAG-CL