Related papers: AutoPrune: Each Complexity Deserves a Pruning Poli…

Structured pruning methods are developed to bridge the gap between the massive scale of neural networks and the limited hardware resources. Most current structured pruning methods rely on training datasets to fine-tune the compressed model,…

DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for…

Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration…

Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their…

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…

In this work, we present FastAV, the first token pruning framework tailored for audio-visual large language models (AV-LLMs). While token pruning has been actively explored in standard large language models (LLMs) and vision-language models…

Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we find that current methods, while adequate for general…

Multimodal Large Language Models (MLLMs) have achieved strong performance across vision-language tasks, but suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal…

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most existing work estimates visual redundancy using a single…

Recent Multimodal Large Language Models(MLLMs) often use a large number of visual tokens to compensate their visual shortcoming, leading to excessive computation and obvious visual redundancy. In this paper, we investigate what kind of…

Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a…

Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Transformer (ViT)…

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that…

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant computational burdens due to long visual sequence inputs. Recent works address this…

Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens. Token pruning alleviates this issue, yet existing approaches face limitations. Attention-based methods rely…

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 Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however,…

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rely on Gumbel-Softmax to approximate discrete selection during training. However, the…

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…