Related papers: Contrastive Regularization over LoRA for Multimoda…

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning…

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the…

Composed Image Retrieval (CIR) involves retrieving a target image based on a composed query of an image paired with text that specifies modifications or changes to the visual reference. CIR is inherently an instruction-following task, as…

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal…

Multi-modal class-incremental learning (MMCIL) seeks to leverage multi-modal data, such as audio-visual and image-text pairs, thereby enabling models to learn continuously across a sequence of tasks while mitigating forgetting. While…

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

In high-stakes medical applications, consistent answering across diverse question phrasings is essential for reliable diagnosis. However, we reveal that current Medical Vision-Language Models (Med-VLMs) exhibit concerning fragility in…

Inverse Reinforcement Learning (IRL) seeks to infer reward functions from expert demonstrations. When demonstrations originate from multiple experts with different intentions, the problem is known as Multi-Intention IRL (MI-IRL). Recent…

Cross-lingual Cross-modal Retrieval (CCR) is an essential task in web search, which aims to break the barriers between modality and language simultaneously and achieves image-text retrieval in the multi-lingual scenario with a single model.…

Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT)…

Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during both training and inference. In real-world scenarios, however,…

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which…

Decoding neural visual representations from electroencephalogram (EEG)-based brain activity is crucial for advancing brain-machine interfaces (BMI) and has transformative potential for neural sensory rehabilitation. While multimodal…

Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot capabilities in various computer vision tasks. However, their application to medical imaging remains challenging due to the high variability and complexity…

Multimodal machine learning has achieved remarkable progress in a wide range of scenarios. However, the reliability of multimodal learning remains largely unexplored. In this paper, through extensive empirical studies, we identify current…

Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring…

Survival prediction of cancers is crucial for clinical practice, as it informs mortality risks and influences treatment plans. However, a static model trained on a single dataset fails to adapt to the dynamically evolving clinical…

Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data…

Medical image segmentation is a fundamental yet challenging task due to the arduous process of acquiring large volumes of high-quality labeled data from experts. Contrastive learning offers a promising but still problematic solution to this…