相关论文: Improved Baselines with Visual Instruction Tuning

Task-oriented semantic communication has emerged as a fundamental approach for enhancing performance in various communication scenarios. While recent advances in Generative Artificial Intelligence (GenAI), such as Large Language Models…

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag…

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…

To operate effectively in the real world, robots should integrate multimodal reasoning with precise action generation. However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to…

State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLaVA-Med and BioMedGPT, primarily depend on scaling model size and data volume, with training driven largely by autoregressive objectives. However, we reveal that this approach…

We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new…

Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were…

With the advent of multi-modal large language models (MLLMs), datasets used for visual question answering (VQA) and referring expression comprehension have seen a resurgence. However, the most popular datasets used to evaluate MLLMs are…

In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, current MLLMs are composed of the well-known…

Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is essential for the generation of detailed and contextually…

Current 3D Large Multimodal Models (3D LMMs) have shown tremendous potential in 3D-vision-based dialogue and reasoning. However, how to further enhance 3D LMMs to achieve fine-grained scene understanding and facilitate flexible human-agent…

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language…

We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g.,…

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…

In the past year, video-based large language models (Video LLMs) have achieved impressive progress, particularly in their ability to process long videos through extremely extended context lengths. However, this comes at the cost of…

Traditional multimodal learning approaches require expensive alignment pre-training to bridge vision and language modalities, typically projecting visual features into discrete text token spaces. We challenge both fundamental assumptions…

Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing…

Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL…

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

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,…