Related papers: Photon: Speedup Volume Understanding with Efficien…
Understanding 3D medical image volumes is a critical task in the medical domain. However, existing 3D convolution and transformer-based methods have limited semantic understanding of an image volume and also need a large set of volumes for…
Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…
Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…
The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on…
Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and…
Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current…
Three-dimensional medical image segmentation is a fundamental yet computationally demanding task due to the cubic growth of voxel processing and the redundant computation on homogeneous regions. To address these limitations, we propose…
Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…
Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains…
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…
Magnetic resonance imaging (MRI) offers the flexibility to image a given anatomic volume under a multitude of tissue contrasts. Yet, scan time considerations put stringent limits on the quality and diversity of MRI data. The gold-standard…
Three-dimensional (3D) medical images, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), are essential for clinical applications. However, the need for diverse and comprehensive representations is particularly…
Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token…
Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment are constrained by massive computational requirements. In particular, the massive amount of…
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still…
Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…
Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference…
The scarcity of annotations poses a significant challenge in medical image analysis. Large-scale pre-training has emerged as a promising label-efficient solution, owing to the utilization of large-scale data, large models, and advanced…
Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…