Related papers: On the Cone Effect and Modality Gap in Medical Vis…
Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts. We evaluate 12 open-weight vision-language models (VLMs) on binary classification across two clinical…
Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…
Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave…
Vision (image and video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained…
In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning approaches often improve…
Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…
Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained…
Modern information systems often involve different types of items, e.g., a text query, an image, a video clip, or an audio segment. This motivates omni-modal embedding models that map heterogeneous modalities into a shared space for direct…
The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the…
Despite significant progress in Vision-Language Pre-training (VLP), current approaches predominantly emphasize feature extraction and cross-modal comprehension, with limited attention to generating or transforming visual content. This gap…
Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…
Combining multiple modalities carrying complementary information through multimodal learning (MML) has shown considerable benefits for diagnosing multiple pathologies. However, the robustness of multimodal models to missing modalities is…
Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…
End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…
The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…
Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…
Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and…
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptimal. Existing approaches uniformly assign positional indices to all tokens, overlooking…
Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches,…
Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…