相关论文: $\Delta$-AttnMask: Attention-Guided Masked Hidden …

Multimodal large language models are typically trained in two stages: first pre-training on image-text pairs, and then fine-tuning using supervised vision-language instruction data. Recent studies have shown that large language models can…

Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders inference efficiency, and prior studies have shown that many…

Vision-Language Pre-training (VLP) is drawing increasing interest for its ability to minimize manual annotation requirements while enhancing semantic understanding in downstream tasks. However, its reliance on image-text datasets poses…

Recent vision-language (VL) studies have shown remarkable progress by learning generic representations from massive image-text pairs with transformer models and then fine-tuning on downstream VL tasks. While existing research has been…

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations…

Medical vision-language models (Med-VLMs) have shown impressive results in tasks such as report generation and visual question answering, but they still face several limitations. Most notably, they underutilize patient metadata and lack…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the importance of semantic data balance, adjusting the distribution of…

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained with visual-question-answering (VQA) datasets could suffer…

Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no works to explore the fundamental natures (\textit{e.g.},…

Recent works have shown that powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs.…

Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to…

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world…