Related papers: OrigamiBench: An Interactive Environment to Synthe…

Despite the remarkable advancements and widespread applications of deep neural networks, their ability to perform reasoning tasks remains limited, particularly in domains requiring structured, abstract thought. In this paper, we investigate…

A key challenge in training Vision-Language Model (VLM) agents, compared to Language Model (LLM) agents, lies in the shift from textual states to complex visual observations. This transition introduces partial observability and demands…

While vision-language models (VLMs) have demonstrated promising capabilities in reasoning and planning for embodied agents, their ability to comprehend physical phenomena, particularly within structured 3D environments, remains severely…

Desktop organization remains challenging for service robots because of heterogeneous objects and diverse manipulation objectives, such as collection and stacking. In this article, a task-oriented framework is presented for organizing planar…

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world…

Large-scale training have propelled significant progress in various sub-fields of AI such as computer vision and natural language processing. However, building robot learning systems at a comparable scale remains challenging. To develop…

Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across diverse environments. However, existing RL benchmarks lack the…

Programming robot behavior in a complex world faces challenges on multiple levels, from dextrous low-level skills to high-level planning and reasoning. Recent pre-trained Large Language Models (LLMs) have shown remarkable reasoning ability…

Innovative HealthTech teams develop Artificial Intelligence (AI) systems in contexts where ethical expectations and organizational priorities must be balanced under severe resource constraints. While Responsible AI practices are expected to…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn…

Large language models (LLMs) and multimodal large language models (MLLMs) have significantly advanced artificial intelligence. However, visual reasoning, reasoning involving both visual and textual inputs, remains underexplored. Recent…

Humans have mental models that allow them to plan, experiment, and reason in the physical world. How should an intelligent agent go about learning such models? In this paper, we will study if models of the world learned in an open-ended…

Exploration is essential for general-purpose robotic learning, especially in open-ended environments where dense rewards, explicit goals, or task-specific supervision are scarce. Vision-language models (VLMs), with their semantic reasoning…

Existing Civil Engineering structures have limited capability to adapt their configurations for new functions, non-stationary environments, or future reuse. Although origami principles provide capabilities of dense packaging and…

As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientifically valid physical models has become a critical gap. Computational mechanics,…

Origami, the ancient art of folding thin sheets, has attracted increasing attention for its practical value in diverse fields: architectural design, therapeutics, deployable space structures, medical stent design, antenna design and…

In cognitive science and AI, a longstanding question is whether machines learn representations that align with those of the human mind. While current models show promise, it remains an open question whether this alignment is superficial or…

Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that their predictions are reliable under the actions they condition on. Existing benchmarks…

Vision-language models (VLMs) perform strongly on many multimodal benchmarks. However, the ability to follow complex visual paths -- a task that human observers typically find straightforward -- remains under-tested. We introduce…