相关论文: MODA: MOdular Duplex Attention for Multimodal Perc…

Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural…

Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data…

Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However,…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a…

Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to…

Multimodal Large Language Models (MLLMs) have achieved strong performance across vision-language tasks, but suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal…

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

Large vision-language models (LVLMs) have demonstrated remarkable multimodal comprehension and reasoning capabilities, but they still suffer from severe object hallucination. Previous studies primarily attribute the flaw to linguistic prior…

Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification. However, most existing approaches rely heavily on…

Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated output. This exposes a more fundamental deficiency in…

Multimodal Large Language Models (MLLMs) have emerged as a central focus in both industry and academia, but often suffer from biases introduced by visual and language priors, which can lead to multimodal hallucination. These biases arise…

Multimodal sentiment analysis utilizes multiple heterogeneous modalities for sentiment classification. The recent multimodal fusion schemes customize LSTMs to discover intra-modal dynamics and design sophisticated attention mechanisms to…

Multimodal Large Language Models (MLLMs), built on powerful language backbones, have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks from a few multimodal demonstrations consisting of images, questions, and answers.…

Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical…

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception…

The potential of multimodal generative artificial intelligence (mAI) to replicate human grounded language understanding, including the pragmatic, context-rich aspects of communication, remains to be clarified. Humans are known to use…

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We…

While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In this work, we position fusion depth, scalability, and…

Audio-driven portrait animation aims to synthesize portrait videos that are conditioned by given audio. Animating high-fidelity and multimodal video portraits has a variety of applications. Previous methods have attempted to capture…

Advancements in deep learning are driven by training models with increasingly larger numbers of parameters, which in turn heightens the computational demands. To address this issue, Mixture-of-Depths (MoD) models have been proposed to…