Related papers: InternVL-X: Advancing and Accelerating InternVL Se…

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility.…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens processed, limiting…

Large Vision-Language Models (LVLMs) are pivotal for real-world AI tasks like embodied intelligence due to their strong vision-language reasoning abilities. However, current LVLMs process entire images at the token level, which is…

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches…

This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs'…

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces…

Large Multimodal Models (LMMs) have achieved significant success across various tasks. These models usually encode visual inputs into dense token sequences, which are then concatenated with textual tokens and jointly processed by a language…

Multimodal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a broad spectrum of domains. However, the large model scale and associated high computational costs pose significant…

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long…

Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation is computationally…

Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a…

Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance,…

Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence length and thousands of visual tokens contributed by…

Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT…

Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in…