相关论文: VisualActBench: Can VLMs See and Act like a Human?

Knowing others' intentions and taking others' perspectives are two core components of human intelligence that are considered to be instantiations of theory-of-mind. Infiltrating machines with these abilities is an important step towards…

Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely…

Multimodal large language models (MLLMs) have shown great potential in perception and interpretation tasks, but their capabilities in predictive reasoning remain under-explored. To address this gap, we introduce a novel benchmark that…

Current benchmarks for evaluating Vision Language Models (VLMs) often fall short in thoroughly assessing model abilities to understand and process complex visual and textual content. They typically focus on simple tasks that do not require…

Real-time human perception is crucial for effective human-robot interaction (HRI). Large vision-language models (VLMs) offer promising generalizable perceptual capabilities but often suffer from high latency, which negatively impacts user…

Sensemaking report writing often requires multiple refinements in the iterative process. While Large Language Models (LLMs) have shown promise in generating initial reports based on human visual workspace representations, they struggle to…

As Vision-Language Models (VLMs) grow in sophistication, their ability to perform reasoning is coming under increasing supervision. While they excel at many tasks, their grasp of fundamental scientific principles, such as physics, remains…

Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend…

Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs…

Despite significant advancements in Large Language Models (LLMs) and Large Vision-Language Models (LVLMs), current models still face substantial challenges in handling complex, multi-turn, and visually-grounded tasks that demand deep…

Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities. However, they lack a grounded understanding of physical dynamics. This limitation arises from training VLMs on static internet-scale…

Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus on reactive responses, overlooking the complexities of…

Reliable evaluation of AI models is critical for scientific progress and practical application. While existing VLM benchmarks provide general insights into model capabilities, their heterogeneous designs and limited focus on a few imaging…

Visual transformation reasoning (VTR) is a vital cognitive capability that empowers intelligent agents to understand dynamic scenes, model causal relationships, and predict future states, and thereby guiding actions and laying the…

Human reasoning can be understood as a cooperation between the intuitive, associative "System-1" and the deliberative, logical "System-2". For existing System-1-like methods in visual activity understanding, it is crucial to integrate…

Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation. However,…

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…

Existing research primarily evaluates the values of LLMs by examining their stated inclinations towards specific values. However, the "Value-Action Gap," a phenomenon rooted in environmental and social psychology, reveals discrepancies…

Large language models (LLMs) have increased interest in vision language models (VLMs), which process image-text pairs as input. Studies investigating the visual understanding ability of VLMs have been proposed, but such studies are still…

Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language…