相关论文: LEIA: Learned Environment for Interactive Architec…
Coupling of physics across length and time scales plays an important role in the response of microstructured materials to external loads. In a multi-scale framework, unresolved (subgrid) meso-scale dynamics is upscaled to the homogenized…
This paper investigates the transformative potential of Generative AI (Gen-AI) technologies, particularly large language models, within the building industry. By leveraging these advanced AI tools, the study explores their application…
This thesis presents a novel framework for analysing the societal impacts of armed conflict by applying principles from engineering and material science. Building on the idea of a "social fabric", it recasts communities as plates with…
Architected metamaterials such as foams and lattices exhibit a wide range of properties governed by microstructural instabilities and emerging phase transformations. Their macroscopic response--including energy dissipation during impact,…
Soils and sediments are soft, amorphous materials with complex microstructures and mechanical properties, that are also building blocks for industrial materials such as concrete. These Earth-mediated materials evolve under prolonged…
We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the…
The IKEA Furniture Assembly Environment is one of the first benchmarks for testing and accelerating the automation of complex manipulation tasks. The environment is designed to advance reinforcement learning from simple toy tasks to complex…
Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages,…
Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…
AI alignment is growing in importance, yet many current approaches learn safety behavior by directly modifying policy parameters, entangling normative constraints with the underlying policy. This often yields opaque, difficult-to-edit…
The true power of computational research typically can lay in either what it accomplishes or what it enables others to accomplish. In this work, both avenues are simultaneously embraced across several distinct efforts existing at three…
In many biological materials such as nacre and bone, the material structure consists of hard grains and soft interfaces, with the interfaces playing a significant role in the material's mechanical behavior. This type of structures has been…
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…
Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support…
Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. Instead, world models are emerging as an alternative…
Map applications are still largely point-and-click, making it difficult to ask map-centric questions or connect what a camera sees to the surrounding geospatial context with view-conditioned inputs. We introduce IMAIA, an interactive Maps…
Natural lifeforms specialise to their environmental niches across many levels; from low-level features such as DNA and proteins, through to higher-level artefacts including eyes, limbs, and overarching body plans. We propose Multi-Level…
Open-source EDA shows promising potential in unleashing EDA innovation and lowering the cost of chip design. This paper presents an open-source EDA project, iEDA, aiming for building a basic infrastructure for EDA technology evolution and…
In the livestock sector, the fragmented data landscape across isolated systems presents a significant challenge, necessitating interoperability and integration. In this article, we introduce the Livestock Event Information Sharing…
This paper presents a novel framework, Artificial Intelligence-Enabled Intelligent Assistant (AIIA), for personalized and adaptive learning in higher education. The AIIA system leverages advanced AI and Natural Language Processing (NLP)…