相关论文: MaMe & MaRe: Matrix-Based Token Merging and Restor…

Masked autoencoders (MAE) have recently succeeded in self-supervised vision representation learning. Previous work mainly applied custom-designed (e.g., random, block-wise) masking or teacher (e.g., CLIP)-guided masking and targets.…

Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and…

Data augmentation is a key technique for improving the robustness of image classification models. However, many recent approaches rely on diffusion-based synthesis or complex feature mixing strategies, which introduce substantial…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

The adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput. To this end several token pruning and merging approaches have been proposed that improve efficiency by…

Visual Auto-Regressive modeling (VAR) has shown promise in bridging the speed and quality gap between autoregressive image models and diffusion models. VAR reformulates autoregressive modeling by decomposing an image into successive…

Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands. To expedite pre-trained ViTs, token pruning and token…

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting…

Displaying high-quality images on edge devices, such as augmented reality devices, is essential for enhancing the user experience. However, these devices often face power consumption and computing resource limitations, making it challenging…

Video transformer models require huge amounts of compute resources due to the spatio-temporal scaling of the input. Tackling this, recent methods have proposed to drop or merge tokens for image models, whether randomly or via learned…

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…

Mixture of Experts (MoE) LLMs face significant obstacles due to their massive parameter scale, which imposes memory, storage, and deployment challenges. Although recent expert merging methods promise greater efficiency by consolidating…

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…

MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability…

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite…

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either…