相关论文: Spatial-Aware Efficient Projector for MLLMs via Mu…

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…

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…

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…

Industrial vision inspection requires high accuracy under stringent resource constraints, yet existing approaches face a fundamental trade-off. Multimodal LLMs (MLLMs) deliver strong reasoning capabilities but incur prohibitive…

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 Multi-Modal Large Language Model (MLLM) refers to an extension of the Large Language Model (LLM) equipped with the capability to receive and infer multi-modal data. Spatial awareness stands as one of the crucial abilities of MLLM,…

Token interaction operation is one of the core modules in MLP-based models to exchange and aggregate information between different spatial locations. However, the power of token interaction on the spatial dimension is highly dependent on…

In Multimodal Large Language Models (MLLMs), a visual projector plays a crucial role in bridging pre-trained vision encoders with LLMs, enabling profound visual understanding while harnessing the LLMs' robust capabilities. Despite the…

Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts. However, most existing methods…

Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning.…

Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliability. Most existing studies focus on the text modality, attributing hallucinations to overly…

In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these systems may additionally rely on human…

With the integration of image modality, the semantic space of multimodal large language models (MLLMs) is more complex than text-only models, making their interpretability more challenging and their alignment less stable, particularly…

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both…

Visual Spatial Reasoning is crucial for enabling Multimodal Large Language Models (MLLMs) to understand object properties and spatial relationships, yet current models still struggle with 3D-aware reasoning. Existing approaches typically…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…

New era has unlocked exciting possibilities for extending Large Language Models (LLMs) to tackle 3D vision-language tasks. However, most existing 3D multimodal LLMs (MLLMs) rely on compressing holistic 3D scene information or segmenting…

Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter…