相关论文: Dragonfly: Multi-Resolution Zoom-In Encoding Enhan…

Vision-language models (VLMs) have achieved remarkable success in scene understanding and perception tasks, enabling robots to plan and execute actions adaptively in dynamic environments. However, most multimodal large language models lack…

The ability of large language models (LLMs) to process visual inputs has given rise to general-purpose vision systems, unifying various vision-language (VL) tasks by instruction tuning. However, due to the enormous diversity in input-output…

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture…

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

Advances in GPT-based large language models (LLMs) are revolutionizing natural language processing, exponentially increasing its use across various domains. Incorporating uni-directional attention, these autoregressive LLMs can generate…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video…

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing users to navigate…

Vision-Language Models (VLMs) have recently experienced significant advancements. However, challenges persist in the accurate recognition of fine details within high resolution images, which limits performance in multiple tasks. This work…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

Vision-language models (VLMs) are highly effective but often underperform on specialized tasks; for example, Llava-1.5 struggles with chart and diagram understanding due to scarce task-specific training data. Existing training data, sourced…

Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple…

The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction --…

Recent advances in AI combine large language models (LLMs) with vision encoders that bring forward unprecedented technical capabilities to leverage for a wide range of healthcare applications. Focusing on the domain of radiology,…

Vision-Language Foundation Models (VLMs), trained on large-scale multimodal datasets, have driven significant advances in Artificial Intelligence (AI) by enabling rich cross-modal reasoning. Despite their success in general domains,…

The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision…

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising…