相关论文: Can Vision-Language Models Solve the Shell Game?

Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and…

Vision language models (VLM) have demonstrated remarkable performance across various downstream tasks. However, understanding fine-grained visual-linguistic concepts, such as attributes and inter-object relationships, remains a significant…

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…

A truly capable AI system must do more than detect objects or recognize activities in isolation. It must form unified, grounded representations of who is acting, what they are doing, and when and where these actions unfold. These…

The enhancement of generalization in robots by large vision-language models (LVLMs) is increasingly evident. Therefore, the embodied cognitive abilities of LVLMs based on egocentric videos are of great interest. However, current datasets…

Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization…

Cross-modal alignment is one key challenge for Vision-and-Language Navigation (VLN). Most existing studies concentrate on mapping the global instruction or single sub-instruction to the corresponding trajectory. However, another critical…

We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using…

Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by generating coordinates as part of their text output, which requires learning a complicated coordinate system and results in a high…

The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and integrating modality-specific encoders. However, LMMs are…

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus…

Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric…

Vision-language models (VLMs) are emerging as powerful generalist tools for remote sensing, capable of integrating information across diverse tasks and enabling flexible, instruction-based interactions via a chat interface. In this work, we…

Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program…

Recent advancements extend Multimodal Large Language Models (MLLMs) beyond standard visual question answering to utilizing external tools for advanced visual tasks. Despite this progress, precisely executing and effectively composing…

We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embodied cognition essential for Human-Robot Interaction (HRI). As a first step toward this goal,…

Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual…

World models - generative models that simulate environment dynamics conditioned on past observations and actions - are gaining prominence in planning, simulation, and embodied AI. However, evaluating their rollouts remains a fundamental…

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…