Related papers: PMR: Prototypical Modal Rebalance for Multimodal L…

Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of…

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on…

While humans excel at continual learning (CL), deep neural networks (DNNs) exhibit catastrophic forgetting. A salient feature of the brain that allows effective CL is that it utilizes multiple modalities for learning and inference, which is…

Graph based molecular representation learning is essential for accurately predicting molecular properties in drug discovery and materials science; however, it faces significant challenges due to the intricate relationships among molecules…

The missing modality problem poses a fundamental challenge in multimodal sentiment analysis, significantly degrading model accuracy and generalization in real world scenarios. Existing approaches primarily improve robustness through prompt…

Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing CL methods only rely on the parameters of the most recent…

Understanding human perceptions presents a formidable multimodal challenge for computers, encompassing aspects such as sentiment tendencies and sense of humor. While various methods have recently been introduced to extract…

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during…

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Multimodal learning enables neural networks to integrate information from heterogeneous sources, but active learning in this setting faces distinct challenges. These include missing modalities, differences in modality difficulty, and…

Neural networks are rapidly gaining popularity in scientific research, but training the models is often very time-consuming. Particularly when the training data samples are large high-dimensional arrays, efficient training methodologies…

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scenarios often exhibit…

Modern recommender systems face critical challenges in handling information overload while addressing the inherent limitations of multimodal representation learning. Existing methods suffer from three fundamental limitations: (1) restricted…

Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model, where queries and candidates can consist of pure text, images, or a combination of both. Previous work has attempted to adopt…

Developing effective multimodal data fusion strategies has become increasingly essential for improving the predictive power of statistical machine learning methods across a wide range of applications, from autonomous driving to medical…

The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both model-specific knowledge distributions and the intrinsic…

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

In this paper, we propose SimMLM, a simple yet powerful framework for multimodal learning with missing modalities. Unlike existing approaches that rely on sophisticated network architectures or complex data imputation techniques, SimMLM…

Many recommender models have been proposed to investigate how to incorporate multimodal content information into traditional collaborative filtering framework effectively. The use of multimodal information is expected to provide more…