Related papers: Spatial-LLaVA: Enhancing Large Language Models wit…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Precise spatial modeling in the operating room (OR) is foundational to many clinical tasks, supporting intraoperative awareness, hazard avoidance, and surgical decision-making. While existing approaches leverage large-scale multimodal…

Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs)…

With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…

This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA…

Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…

Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies. While recent studies have yielded valuable insights into the mechanisms of textual LLMs, the mechanisms of Multi-modal…

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

The development of Large Vision-Language Models (LVLMs) is striving to catch up with the success of Large Language Models (LLMs), yet it faces more challenges to be resolved. Very recent works enable LVLMs to localize object-level visual…

Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The merging of these data domains represents a significant paradigm shift with far-reaching…

We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language model (LLM) that can jointly capture detailed spatial semantics and long-range temporal context without exceeding the token budget of commonly used…

Recent advances in multimodal large language models (LLMs) have highlighted their potential for medical and surgical applications. However, existing surgical datasets predominantly adopt a Visual Question Answering (VQA) format with…

Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning. We study why VLMs, such as LLaVA, underutilize spatial cues despite having positional encodings and spatially rich vision encoder…

The Large Visual-Language Models (LVLMs) have significantly advanced image understanding. Their comprehension and reasoning capabilities enable promising applications in autonomous driving scenarios. However, existing research typically…

Despite significant progress, existing research on Multimodal Large Language Models (MLLMs) mainly focuses on general visual understanding, overlooking the ability to integrate textual context associated with objects for a more…

Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images…

Do we still need to represent objects explicitly in multimodal large language models (MLLMs)? To one extreme, pre-trained encoders convert images into visual tokens, with which objects and spatiotemporal relationships may be implicitly…

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent…

Vision-language models for Earth observation (EO) typically rely on the visual spectrum of data as the only model input, thus failing to leverage the rich spectral information available in the multispectral channels recorded by satellites.…

Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between…