Related papers: CS-VLM: Compressed Sensing Attention for Efficient…

Hallucinations in large vision-language models (LVLMs) often stem from the model's sensitivity to image tokens during decoding, as evidenced by attention peaks observed when generating both real and hallucinated entities. To address this,…

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…

Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retraining. However,…

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

The capability of the self-attention mechanism to model the long-range dependencies has catapulted its deployment in vision models. Unlike convolution operators, self-attention offers infinite receptive field and enables compute-efficient…

Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window and high computational cost of processing high-resolution image inputs and videos.…

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…

Large Vision-Language Models (LVLMs) can accurately locate key objects in images, yet their attention to these objects tends to be very brief. Motivated by the hypothesis that sustained focus on key objects can improve LVLMs' visual…

Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos.…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing, whose effectiveness is mainly attributed to its multi-head attention (MHA)…

Recent research suggests that Vision Language Models (VLMs) often rely on inherent biases learned during training when responding to queries about visual properties of images. These biases are exacerbated when VLMs are asked highly specific…

Large multimodal models (LMMs) "see" images by leveraging the attention mechanism between text and visual tokens in the transformer decoder. Ideally, these models should focus on key visual information relevant to the text token. However,…

This paper introduces ConvShareViT, a novel deep learning architecture that adapts Vision Transformers (ViTs) to the 4f free-space optical system. ConvShareViT replaces linear layers in multi-head self-attention (MHSA) and Multilayer…

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…

The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources.…

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational…

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA)…