相关论文: SAILViT: Towards Robust and Generalizable Visual B…

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to…

Visual encoding followed by token condensing has become the standard architectural paradigm in multi-modal large language models (MLLMs). Many recent MLLMs increasingly favor global native- resolution visual encoding over slice-based…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Vision transformers (ViTs) are widely employed in multimodal large language models (MLLMs) for visual encoding. However, they exhibit inferior performance on tasks regarding fine-grained visual perception. We attribute this to the…

The paper proposes an efficient structure for enhancing the performance of mobile-friendly vision transformer with small computational overhead. The vision transformer (ViT) is very attractive in that it reaches outperforming results in…

Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language…

The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal…

Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain,…

Vision Transformers (ViTs) excel in semantic segmentation but demand significant computation, posing challenges for deployment on resource-constrained devices. Existing token pruning methods often overlook fundamental visual data…

The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws…

Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performance. However, the integration of multi-layer visual features…

Large Vision-Language Models (LVLMs) demonstrate a promising direction for assisting individuals with blindness or low-vision (BLV). Yet, measuring their true utility in real-world scenarios is challenging because evaluating whether their…

Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive…

For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs' output remains sensitive to small spatial shifts in the input, i.e.,…

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models…

What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale…

With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy. However, it remains unclear how their…

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with…

Modern computer vision is converging on a closed loop in which perception, reasoning and generation mutually reinforce each other. However, this loop remains incomplete: the top-down influence of high-level reasoning on the foundational…

The rapid advancements in large language models (LLMs) have unlocked their potential for multimodal tasks, where text and visual data are processed jointly. However, applying LLMs to medical imaging, particularly for chest X-rays (CXR),…