13 accepted papers
Recent advances in vision-language models have shown strong performance across diverse multimodal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike natural images, document images contain large backgrounds and only spar
Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm has recently been extended to Vision-Language Models (VLMs)
Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Existing Multimodal Large Language Model (MLLM) approaches often overlook these characteristics, resulting in uninformative a
Vision-Language Models (VLMs) have been widely used in various visual recognition tasks due to their remarkable generalization capabilities. As these models grow in size and complexity, fine-tuning becomes costly, emphasizing the need to reuse adaptation knowledge from
For the deployment of neural networks in resource-constrained environments, prior works have built lightweight architectures with convolution and attention for capturing local and global dependencies, respectively. Recently, the state space model (SSM) has emerged as an effective operation for globa…
Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory access. To reduce the computation cost of self-attention, prior…
Large Vision-Language Models (LVLMs) have recently shown promising results on various multimodal tasks, even achieving human-comparable performance in certain cases. Nevertheless, LVLMs remain prone to hallucinations–they often rely heavily on a single modality or memorize training data without prop
Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However these works faced the speed-accuracy trade-off caused by the loss of informa…
Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However these video transformers suffer from heavy computational costs induced by the massive number of tokens across the entire video frames which has been the ma…
In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to down- stream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre- trained weights frozen. However, learnable prompts can affect the internal r…
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clouds due to their quadratic cost in the number of points. In this paper, we prese…
Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity. Also, recent studies of saliency-aware Mixup in the image do…
Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach to compensate for the scarcity of data, it has been less explored in the point cloud literature. In this paper, we prop…