Related papers: PPT: Token Pruning and Pooling for Efficient Visio…

Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…

Vision-Language Models (VLMs) have become central to autonomous driving systems, yet their deployment is severely bottlenecked by the massive computational overhead of multi-view camera and multi-frame video input. Existing token pruning…

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.…

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

While Vision Transformers (ViTs) are extremely effective at computer vision tasks and are replacing convolutional neural networks as the new state-of-the-art, they are complex and memory-intensive models. In order to effectively run these…

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through…

Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices…

Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to…

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,…

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in real-world scenarios. To achieve…

Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by the language model.…

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not…

Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However,…

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose…

Vision Transformers (ViTs) face severe computational bottlenecks due to the quadratic complexity of self-attention at high resolutions. Existing token reduction methods rely on local metrics - such as single-layer attention scores - that…