Related papers: Training-free Token Reduction for Vision Mamba

Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures. Existing works empower the models by massive data, such as large-scale pre-training…

Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden. Recent efforts have been made to tackle this issue by pruning visual…

Convolutional neural network (CNN) and Transformer-based architectures are two dominant deep learning models for polyp segmentation. However, CNNs have limited capability for modeling long-range dependencies, while Transformers incur…

Multimodal Large Language Models (MLLMs) have attracted much attention for their multifunctionality. However, traditional Transformer architectures incur significant overhead due to their secondary computational complexity. To address this…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

The rapid advancement of Multimodal Large Language Models (MLLMs) has led to remarkable performances across various domains. However, this progress is accompanied by a substantial surge in the resource consumption of these models. We…

Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

In multivariate time-series forecasting (MTSF), extracting the temporal correlations of the input sequences is crucial. While popular Transformer-based predictive models can perform well, their quadratic computational complexity results in…

Capturing long-range dependencies (LRD) efficiently is a core challenge in visual recognition, and state-space models (SSMs) have recently emerged as a promising alternative to self-attention for addressing it. However, adapting SSMs into…

Large Vision-Language Models (LVLMs) have advanced multimodal learning but face high computational costs due to the large number of visual tokens, motivating token pruning to improve inference efficiency. The key challenge lies in…

Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as ToMe, rely on GPU-inefficient operations…

Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by…

The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods…

Rotation equivariance constitutes one of the most general and crucial structural priors for visual data, yet it remains notably absent from current Mamba-based vision architectures. Despite the success of Mamba in natural language…

Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to reduce ViT's $O(n^2)$ complexity by pruning unimportant…

We present MambaNetBurst, a compact tokenizer-free byte-level sequence classifier for network burst classification based on a Mamba-2 backbone. In contrast to most recent strong traffic-classification and intrusion-detection approaches, our…

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…

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly…