相关论文: Kernel-based Unsupervised Embedding Alignment for …

Despite recent successes, LVLMs or Large Vision Language Models are prone to hallucinating details like objects and their properties or relations, limiting their real-world deployment. To address this and improve their robustness, we…

Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives.…

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper…

Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting…

Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce…

Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence.…

Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on…

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…

Vision Language Models (VLMs) encode multimodal inputs over large, complex, and difficult-to-interpret architectures, which limit transparency and trust. We propose a Multimodal Inversion for Model Interpretation and Conceptualization…

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness…

Rapid and reliable qualification of advanced materials remains a bottleneck in industrial manufacturing, particularly for heterogeneous structures produced via non-conventional additive manufacturing processes. This study introduces a novel…

Does seeing always mean knowing? Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components, often using CLIP-ViT as vision backbone. However, these models frequently encounter a core issue of…

The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for…

Multi-modal large language models (MLLMs) have achieved remarkable success in fine-grained visual understanding across a range of tasks. However, they often encounter significant challenges due to inadequate alignment for fine-grained…

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this…

Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks…

Recent vision-language foundation models still frequently produce outputs misaligned with their inputs, evidenced by object hallucination in captioning and prompt misalignment in the text-to-image generation model. Recent studies have…

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential, particularly in zero-shot classification across diverse distribution shifts. Building on existing evaluations of overall classification robustness, this…

Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual and textual concepts are naturally…