相关论文: Evaluating point-light biological motion in multim…

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…

In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL…

Multimodal large language models (MLLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. Despite its success in language understanding, it is critical to evaluate the…

While multimodal large language models (MLLMs) are increasingly applied in human-centred AI systems, their ability to understand complex social interactions remains uncertain. We present an exploratory study on aligning MLLMs with…

As general-purpose tools, Large Language Models (LLMs) must often reason about everyday physical environments. In a question-and-answer capacity, understanding the interactions of physical objects may be necessary to give appropriate…

In an era defined by the explosive growth of data and rapid technological advancements, Multimodal Large Language Models (MLLMs) stand at the forefront of artificial intelligence (AI) systems. Designed to seamlessly integrate diverse data…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including data augmentation and synthetic data generation. This work explores the use of LLMs to generate rich textual descriptions for motion…

Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where models perform step-by-step reasoning under complete…

The realization of intelligent robots, operating autonomously and interacting with other intelligent agents, human or artificial, requires the integration of environment perception, reasoning, and action. Classic Artificial Intelligence…

Large multimodal models (LMMs) show strong visual-linguistic reasoning but their capacity for spatial decision-making and action remains unclear. In this work, we investigate whether LMMs can achieve embodied spatial action like human…

Vision-Language Navigation (VLN) is a challenging task that requires an embodied agent to perform action-level modality alignment, i.e., make instruction-asked actions sequentially in complex visual environments. Most existing VLN agents…

The Vision Language Model (VLM) excels in aligning vision and language representations, and prompt learning has emerged as a key technique for adapting such models to downstream tasks. However, the application of prompt learning with VLM in…

The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the…

Although Vision-Language Models (VLM) have demonstrated impressive planning and reasoning capabilities, translating these abilities into the physical world introduces significant challenges. Conventional Vision-Language-Action (VLA) models,…

While remarkable progress has been made on supervised skeleton-based action recognition, the challenge of zero-shot recognition remains relatively unexplored. In this paper, we argue that relying solely on aligning label-level semantics and…

Reinforcement learning in large reasoning models enables learning from feedback on their outputs, making it particularly valuable in scenarios where fine-tuning data is limited. However, its application in multi-modal human activity…

The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on…

Behavior-driven development (BDD) is an Agile testing methodology fostering collaboration among developers, QA analysts, and stakeholders. In this manuscript, we propose a novel approach to enhance BDD practices using large language models…

Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significant performance…

This paper introduces ACTLLM (Action Consistency Tuned Large Language Model), a novel approach for robot manipulation in dynamic environments. Traditional vision-based systems often struggle to learn visual representations that excel in…