Related papers: Neurosymbolic Grounding for Compositional World Mo…
We present a commonsense, qualitative model for the semantic grounding of embodied visuo-spatial and locomotive interactions. The key contribution is an integrative methodology combining low-level visual processing with high-level,…
Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets. This complexity has held back progress in areas, such as robotics, where robust task-general…
As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…
Neuro-symbolic learning generally consists of two separated worlds, i.e., neural network training and symbolic constraint solving, whose success hinges on symbol grounding, a fundamental problem in AI. This paper presents a novel, softened…
Learned image compression methods have shown impressive performance but are often highly specialized for either human perception or specific machine vision tasks. This specialization limits their versatility and requires costly retraining…
Neural-symbolic approaches to machine learning incorporate the advantages from both connectionist and symbolic methods. Typically, these models employ a first module based on a neural architecture to extract features from complex data.…
This paper presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The core issue here is the grounding of referring expressions: infer objects and their relationships from input…
Addressing the limitations of text as a source of accurate layout representation in text-conditional diffusion models, many works incorporate additional signals to condition certain attributes within a generated image. Although successful,…
Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as…
Grounding object properties and relations in 3D scenes is a prerequisite for a wide range of artificial intelligence tasks, such as visually grounded dialogues and embodied manipulation. However, the variability of the 3D domain induces two…
Despite their impressive realism, modern text-to-image models still struggle with compositionality, often failing to render accurate object counts, attributes, and spatial relations. To address this challenge, we present a training-free…
We present the Elements project, a lightweight, open-source, computational science and computer graphics (CG) framework, tailored for educational needs, that offers, for the first time, the advantages of an Entity-Component-System (ECS)…
Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to understand the…
Reliable assessment of safe landing sites in unstructured environments is essential for deploying Unmanned Aerial Vehicles (UAVs) in real-world applications such as delivery, inspection, and surveillance. Existing learning-based approaches…
Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components.…
The highly influential framework of conceptual spaces provides a geometric way of representing knowledge. It aims at bridging the gap between symbolic and subsymbolic processing. Instances are represented by points in a high-dimensional…
Based on the cosmological principle only, the method of describing the evolution of the Universe, called cosmography, is in fact a kinematics of cosmological expansion. The effectiveness of cosmography lies in the fact that it allows, based…
Existing end-to-end autonomous driving models rely heavily on purely data-driven inductive reasoning. This "black-box" nature leads to a lack of interpretability and absolute safety guarantees in complex, long-tail scenarios. To overcome…
Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the physical world and generate appropriate embodied decisions…
We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge. In the design, the spatial…