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

In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference cost. Many works aim to address this issue by removing…

Vision Transformers (ViTs) have emerged as powerful backbones in computer vision, outperforming many traditional CNNs. However, their computational overhead, largely attributed to the self-attention mechanism, makes deployment on…

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution…

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight and token pruning are…

Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is normally fine-tuned on the original training dataset to recover…

Large-scale vision generative models, including diffusion and flow models, have demonstrated remarkable performance in visual generation tasks. However, transferring these pre-trained models to downstream tasks often results in significant…

Recently, state-of-the-art approaches for pruning large pre-trained models (LPMs) have demonstrated that the training-free removal of non-critical residual blocks in Transformers is viable for reducing model size, achieving results that…

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

Vision Transformers (ViTs) achieve state-of-the-art performance but suffer from the $O(N^2)$ complexity of self-attention, making inference costly for high-resolution inputs. To address this bottleneck, token pruning has emerged as a…

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…

Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token sparsity through token pruning, but permanently discarding visual content…

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Large Vision-Language Models (LVLMs) represent a significant advancement toward achieving superior multimodal capabilities by enabling powerful Large Language Models (LLMs) to understand visual input. Typically, LVLMs utilize visual…

The widespread availability of pre-trained vision models has enabled numerous deep learning applications through their transferable representations. However, their computational and storage costs often limit practical deployment.…

Neural network compression has gained increasing attention in recent years, particularly in computer vision applications, where the need for model reduction is crucial for overcoming deployment constraints. Pruning is a widely used…

Modern neural networks, although achieving state-of-the-art results on many tasks, tend to have a large number of parameters, which increases training time and resource usage. This problem can be alleviated by pruning. Existing methods,…

Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their latency, high computational costs and memory demands pose…

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning,…

Tensor program tuning is essential for the efficient deployment of deep neural networks. Search-based approaches have demonstrated scalability and effectiveness in automatically finding high-performance programs for specific hardware.…

Frozen-backbone transfer with Vision Transformers faces two under-addressed issues: optimization instability when adapters are naively inserted into a fixed feature extractor, and the absence of principled guidance for setting adapter…