相关论文: Zero-TPrune: Zero-Shot Token Pruning through Lever…

Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising approach for improving frozen LLMs via interpretable interventions.…

Token reduction accelerates Multimodal Large Language Models (MLLMs) by reducing excessive tokens, but overlooks structural redundancy differences, where critical and redundant modules process identical token loads. For fine-grained…

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

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…

Large models achieve strong performance on Vision-and-Language Navigation (VLN) tasks, but are costly to run in resource-limited environments. Token pruning offers appealing tradeoffs for efficiency with minimal performance loss by reducing…

Multimodal large language models (MLLMs) have shown remarkable capabilities in a wide range of vision-language tasks. However, the large number of visual tokens introduces significant computational overhead. To address this issue, visual…

Although Large Vision Language Models (LVLMs) have demonstrated remarkable performance in image understanding tasks, their computational efficiency remains a significant challenge, particularly on resource-constrained devices due to the…

While deep neural networks have demonstrated remarkable performance across various tasks, they typically require massive training data. Due to the presence of redundancies and biases in real-world datasets, not all data in the training…

Convolutional neural networks are prevailing in deep learning tasks. However, they suffer from massive cost issues when working on mobile devices. Network pruning is an effective method of model compression to handle such problems. This…

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead…

In today's world, a vast amount of data is being generated by edge devices that can be used as valuable training data to improve the performance of machine learning algorithms in terms of the achieved accuracy or to reduce the compute…

As deep neural networks (DNNs) are increasingly deployed on edge devices, optimizing models for constrained computational resources is critical. Existing auto-pruning methods face challenges due to the diversity of DNN models, various…

Convolutional neural networks (CNNs) are becoming increasingly deeper, wider, and non-linear because of the growing demand on prediction accuracy and analysis quality. The wide and deep CNNs, however, require a large amount of computing…

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

Applying deep neural networks to 3D point cloud processing has attracted increasing attention due to its advanced performance in many areas, such as AR/VR, autonomous driving, and robotics. However, as neural network models and 3D point…

Pruning is a widely used method for compressing Deep Neural Networks (DNNs), where less relevant parameters are removed from a DNN model to reduce its size. However, removing parameters reduces model accuracy, so pruning is typically…

Structured pruning is essential for efficient deployment of Large Language Models (LLMs). The varying sensitivity of LLM sub-blocks to pruning necessitates the identification of optimal non-uniformly pruned models. Existing methods evaluate…

Convolutional Neural Networks (CNN) are widely used in many computer vision tasks. Yet, their increasing size and complexity pose significant challenges for efficient deployment on resource-constrained platforms. Hence, network pruning has…

In response to the rising interest in large multimodal models, we introduce Cross-Attention Token Pruning (CATP), a precision-focused token pruning method. Our approach leverages cross-attention layers in multimodal models, exemplified by…

While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies.…