Related papers: DeepStack: Deeply Stacking Visual Tokens is Surpri…

In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to…

Large multimodal models (LMMs) have gained impressive performance due to their outstanding capability in various understanding tasks. However, these models still suffer from some fundamental limitations related to robustness and…

This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition…

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of biomedical captions from large-scale open source literature…

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…

Over the past few years, the advancement of Multimodal Large Language Models (MLLMs) has captured the wide interest of researchers, leading to numerous innovations to enhance MLLMs' comprehension. In this paper, we present AdaptVision, a…

Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…

Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel…

The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local…

Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality,…

To utilize visual information, Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder. The completeness and accuracy of visual perception significantly influence the precision of spatial reasoning,…

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…

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language…

Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…

Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we interestingly find that language-only models, when provided…

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures…

Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by…

Large Multimodal Models (LMMs) such as LLaVA have shown strong performance in visual-linguistic reasoning. These models first embed images into a fixed large number of visual tokens and then feed them into a Large Language Model (LLM).…

Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while…