Related papers: MetaAID 2.0: An Extensible Framework for Developin…
Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. Previous approaches often…
The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…
Traditional Business Process Management (BPM) struggles with rigidity, opacity, and scalability in dynamic environments while emerging Large Language Models (LLMs) present transformative opportunities alongside risks. This paper explores…
The emergence of the metaverse - envisioned as a hyperreal virtual universe enabling boundless human interaction - has the potential to revolutionize our conception of media. This transformation could alter society as we know it. This paper…
Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem. To tackle this, the pre-training mechanism has been widely adopted, which attempts to leverage large-scale…
Explanations are crucial for building trustworthy AI systems, but a gap often exists between the explanations provided by models and those needed by users. To address this gap, we introduce MetaExplainer, a neuro-symbolic framework designed…
Humanoid robots, with their human-like form, are uniquely suited for interacting in environments built for people. However, enabling humanoids to reason, plan, and act in complex open-world settings remains a challenge. World models, models…
This systematic literature review paper explores perspectives on the ideal metaverse from user experience, business, and national levels, considering both academic and industry viewpoints. The study examines the metaverse as a…
The Metaverse emerges by integrating highly-distributed, complex, and interconnecting technologies. These technologies need to be formally verified and evaluated through formal modelling before executing them in real-world applications, in…
While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization…
Achieving autonomous and versatile whole-body loco-manipulation remains a central barrier to making humanoids practically useful. Yet existing approaches are fundamentally constrained: retargeted data are often scarce or low-quality;…
Unsupervised Environment Design (UED) is a paradigm for automatically generating a curriculum of training environments, enabling agents trained in these environments to develop general capabilities, i.e., achieving good zero-shot transfer…
The metaverse promises unprecedented immersive digital experiences but also raises critical privacy concerns as vast amounts of personal and behavioral data are collected. As immersive technologies blur the boundaries between physical and…
As robots enter human workspaces, there is a crucial need for them to comprehend embodied human instructions, enabling intuitive and fluent human-robot interaction (HRI). However, accurate comprehension is challenging due to a lack of…
The metaverse, i.e., the collection of technologies that provide a virtual twin of the real world via mixed reality, internet of things, and others, is gaining prominence. However, the metaverse faces challenges as it grows toward…
We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual…
Artificial Intelligence (AI), particularly through the advent of large-scale generative AI (GenAI) models such as Large Language Models (LLMs), has become a transformative element in contemporary technology. While these models have unlocked…
Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…
Innovators transform the world by understanding where services are successfully meeting customers' needs and then using this knowledge to identify failsafe opportunities for innovation. Pre-trained models have changed the AI innovation…
Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To…